MCP servers › ai.letsship › ship

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.letsship/ship

Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests. — the publisher's description

5 of 5 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedversion 0.24.0streamable HTTP72 tools

Summary

ai.letsship/ship is a remote MCP server listed in the official MCP registry at version 0.24.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 72 tools, 0 resources and 0 prompts.

Record checks

5 of 5 record checks met · 4 do not apply

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
met: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 1 star (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Repository: public
Tools: 72
Described as changing data: 38 of 72 toolsAI-classified
Mainly works on: accounts and data in outside web services; cloud accounts, servers or DevOps toolsAI-classified
Topic: developer-toolsAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 25 tools whose name or declaration suggests they change data (start_credit_checkout, update_team_subscription, update_project, create_mission, set_agents_override and 20 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

38 tools are described as changing something (start_credit_checkout, update_team_subscription, request_more_credits, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 0.24.0, published 2026-10-12 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-12 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.24.0 (published 2026-10-12).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

72tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services; cloud accounts, servers or DevOps tools.

38 of 72 tools are described as changing something (creating, editing, deleting, sending or running).

healthzreads or searches
“Returns the upstream API status, environment, and version.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
whoamion 178 other serversreads or searches
“Returns the caller's identity, org, role, role-derived RBAC capabilities, and token scopes.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_setup_progresson 2 other serversreads or searches
“Read what the workspace has set up with SHIP so far, as the console's setup checklist shows it: up to 13 milestones in three groups, taken in order (get started, make it yours, make it autonomous).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_billingon 7 other serversreads or searches
“Read the workspace's credit balance by source and expiry, whether a new mission would start now, the per-mission credit ceiling, the project allowance and recent usage.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
list_billing_ledgerreads or searches
“List where the workspace's credits went, newest first: one entry per mission (its start, each further 3 agent-hours, and messages charged before messages became free), per grant, per adjustment and p…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- cursorstring“nextCursor from the previous page; omit for the newest entries.”
- limitinteger“Entries per page, 1-100 (default 50).”
list_credit_offersreads or searches
“List what SHIP sells: the credit packs (credits, the price in US dollars before tax, which checkout adds for the buyer's location, and the price per credit), the monthly plans under `team.plans` (Sta…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
start_credit_checkoutmoves moneydescribed as changing data
“Opens a payment page and returns its URL.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
5 inputs, 2 required
- offerstringrequired“A pack, team or team_credits, from list_credit_offers.”
- teamPlanstring“The plan to start, for offer team only: starter or scale, from list_credit_offers.”
- quantityinteger“Credits for team_credits, within the range list_credit_offers gives; omit for a pack or a plan.”
- startNowbooleanrequired“Records the buyer's own consent to start the credits at once, during the withdrawal period, against this text: "Start my credits now, so they can be used durin…”
- idempotencyKeystring“Reuse on retry to get the same page back.”
update_team_subscriptioncreates or changes datadescribed as changing data
“Change the workspace's monthly plan subscription: plan switches between starter and scale from the next renewal on (nothing is charged or refunded for the current month; passing the current plan drop…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs
- planstring“The plan from the next renewal on: starter or scale, from list_credit_offers.”
- cancelAtPeriodEndboolean“true ends the subscription at the end of the paid month; false resumes it.”
request_more_creditssends messagesdescribed as changing data
“Ask for more credits for the workspace, saying what they are for.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- messagestringrequired“What the credits are for.”
get_noticeson 1 other serverreads or searches
“Read what needs attention in the workspace, critical first: a tracker connection its vendor no longer accepts (missions cannot start or report back until someone reconnects it), or credits running ou…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
dismiss_noticecreates or changes datadescribed as changing data
“Close a notice for the person this token acts for, as the console's close button does.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- noticeIdstringrequired“The notice's id from get_notices, e.g.”
mark_setup_stepcreates or changes datadescribed as changing data
“Mark a step of the setup checklist completed or skipped for the person this token acts for, as the console's Mark as complete and Skip controls do; open removes the mark.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- stepstring“The milestone id from get_setup_progress.”
- groupstring“A group id: marks every open step of the group.”
- markstringrequired“open removes the caller's mark.”

Show 60 more tools

list_projectson 157 other serversreads or searches
“List the projects accessible to the calling principal.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger“Max results (default 20)”
- cursorstring“Opaque pagination cursor from a previous call”
get_projecton 111 other serversreads or searches
“Fetch a single project by its UUID.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- projectIdstringrequired“Project UUID”
update_projecton 37 other serverscreates or changes datadescribed as changing data
“Change the settings of one project; a field you leave out keeps its value.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
9 inputs, 1 required
- projectIdstringrequired“Project id, from list_projects”
- namestring“A new name”
- statusstring“active, paused or archived”
- autoMergeboolean“true merges a ready pull request without a person”
- issueCodestring“A GitHub Issues project's issue id prefix, 2-5 characters; only new ids use it”
- defaultSandboxTemplateIdstring or null“A sandbox id (sbt_...) from list_sandbox_templates, or null for the platform base”
- repoFullNamestring“owner/repo of the repository to connect, through the organization's GitHub connection”
- linearTeamKeystring“The key of the Linear team to connect, e.g.”
- jiraProjectIdstring“A Jira project's numeric id on the project's Jira site, e.g.”
start_missionruns code or commandsdescribed as changing data
“Hand a mission off to the AI agent team.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstringrequired“Project id the mission belongs to”
- startAtstring“Pipeline stage to enter at; omit for the default full run starting at the planner”
- planstring“Hand-off plan markdown, for startAt='builder'”
- prNumberinteger“Existing open PR number, required for startAt='reviewer' or startAt='qa'”
- agentsobject“Per-role harness/model override for THIS mission only; overrides ship.yml without changing it”
create_missionon 1 other serverruns code or commandsdescribed as changing data
“Create the tracker issue AND start the run in one call, for work that has no issue yet.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
8 inputs, 1 required
- projectIdstringrequired“Project id the mission belongs to”
- titlestring“Issue title.”
- descriptionstring“Issue body; acceptance criteria written here are parsed as they would be on any issue”
- labelsarray“Tracker labels to apply”
- entryStartAtstring“Pipeline stage to enter at; omit for the default full run starting at the planner”
- entryPlanstring“Hand-off plan markdown, for entryStartAt='builder'”
- entryPrNumberinteger“Existing open PR number, required for entryStartAt='reviewer' or 'qa'”
- agentsobject“Per-role harness/model override for THIS mission only; overrides ship.yml without changing it”
set_agents_overridecreates or changes datadescribed as changing data
“Patch one role's harness/model/effort/prompt for a single mission, layered over ship.yml per-field (a role or field this call omits keeps resolving from ship.yml — SHIP-337).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
15 inputs, 3 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstringrequired“Project id the mission belongs to”
- rolestringrequired“The role this override entry patches”
- harnessstring“The code harness this role runs on for this mission”
- modelstring“The model id this role uses for this mission.”
- effortstring“Reasoning effort for this role, mapped to the harness's own control at dispatch: low, medium, high or xhigh, and also max on claude-code.”
- checkpointboolean“Pause the pipeline after this role's stage completes”
- rejectOnstring“Review rejection threshold — only meaningful on the reviewer role”
- promptContentstring“Inline prompt-experiment body, capped at 30,000 characters.”
- promptPathstring“Repo-relative path to an L2 prompt file.”
- promptRefstring“Git ref for promptPath — only meaningful alongside promptPath.”
- promptModestring“How this prompt relates to the repo's own .ship/agents/<role>.md (or ship.yml-pointed) layer.”
- sandboxstring“Sandbox name or id this role starts in for this mission (beats ship.yml and the project default)”
- sizestring or object“Container size for this role on this mission”
- baseBranchstring“Override the pipeline's fork/target branch for this mission”
get_agents_overridereads or searches
“Read the per-issue agents/baseBranch override record for one mission, or null when unset.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstringrequired“Project id the mission belongs to”
send_mission_instructionsends messagesdescribed as changing data
“Tell a mission what to change.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 2 required
- issueIdstringrequired“Issue id the mission is tracked under, e.g.”
- bodystringrequired“What the agents should do.”
- kindstring“follow_up (default) dispatches the builder; note records context and dispatches nothing”
clear_agents_overridedeletesdescribed as changing data
“Delete the per-issue agents/baseBranch override — the mission resolves from ship.yml again.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstringrequired“Project id the mission belongs to”
list_missionson 6 other serversreads or searches
“List missions in the caller's accessible projects, newest activity first, with total for paging.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- projectIdstring“Filter to one project id”
- activitystring“Filter by what the mission does now”
- searchstring“Match the issue id, title, owner or repository”
- limitinteger“Page size (default 25).”
- offsetinteger“Rows to skip, for the next page”
get_missionon 5 other serversreads or searches
“Fetch one mission.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstring“Narrow an issue id that two projects share”
- orgSlugstring“Narrow an issue id to one org”
- viewstring“summary (default) for the state, runs and proof run; full for every stage, event and outcome”
pause_missioncreates or changes datadescribed as changing data
“Hold a mission before its next stage.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
resume_missiondescribed as changing data
“Continue a paused mission.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
stop_missiondeletesdescribed as changing data
“Hard-stop a mission: every agent run of it stops and its work in progress is lost.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
approve_mission_ceilingdescribed as changing data
“A mission that reached its credit limit pauses until a member lets it continue.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- projectIdstringrequired“Project id the mission belongs to (get_mission's summary.projectId)”
merge_missiondescribed as changing data
“Merge the mission's open pull request on GitHub with the repository's own merge method; the mission then becomes done, and the merge cannot be undone from here.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
decline_missionon 1 other serverdeletesdescribed as changing data
“Close the mission's open pull request on GitHub without merging it; the mission becomes declined, and no call here reopens it.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
set_mission_auto_mergecreates or changes datadescribed as changing data
“Set whether SHIP merges this mission's pull request by itself once the checks, the review and the test pass.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- enabledbooleanrequired“true merges the pull request once it is ready; false leaves the merge to a person”
archive_missiondescribed as changing data
“Hide a finished mission from list_missions and the board.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
unarchive_missioncreates or changes datadescribed as changing data
“Show an archived mission in list_missions and on the board again.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
set_mission_dispositioncreates or changes datadescribed as changing data
“Record a person's reason for how a mission ended, which the delivery statistics use: product (real work, judged on its merits), probe (a test on purpose), superseded (another mission replaced it: giv…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
3 inputs, 2 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- dispositionstring or nullrequired“product, probe, superseded or takeover; null clears a disposition set by mistake”
- supersededBystring“The issue id of the mission that replaced this one, for disposition superseded only”
list_scheduled_taskson 1 other serverreads or searches
“List recurring agent missions (scheduled tasks) across the caller's accessible projects — schedule, enabled state, and next/last fire time for each.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- projectIdstring“Only the scheduled tasks of this project”
list_scheduled_task_templatesreads or searches
“Read-only gallery of curated scheduled task templates — a prepared prompt plus a suggested cadence.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_scheduled_taskreads or searches
“Fetch one scheduled task by id: its project, name, prompt, triggers (schedule), labels, template key, skip-if-previous-open setting, enabled state, and next/last run times.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- scheduledTaskIdstringrequired“Scheduled task id, e.g.”
create_scheduled_taskcreates or changes datadescribed as changing data
“Create a recurring agent mission.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
12 inputs, 6 required
- projectIdstringrequired“Project id the scheduled task belongs to”
- namestringrequired“Scheduled task name, shown in the console and used in the issue title”
- promptstringrequired“Becomes the created issue's description verbatim on every fire”
- intervalstringrequired“Fire cadence.”
- timestringrequired“24-hour wall-clock time in `timezone`, e.g.”
- timezonestringrequired“IANA timezone id, e.g.”
- weekdaystring“Day of week — required when interval is 'weekly'.”
- dayOfMonthinteger“Day of month, 1-28 — required when interval is 'monthly' (capped at 28 so every month has the day).”
- labelsarray“Tracker label names put on every issue this scheduled task files (default none).”
- templateKeystring“Attribution only, when authored from a template — see list_scheduled_task_templates”
- skipIfPreviousOpenboolean“Skip a scheduled fire while the previous fire's mission is still open (default true — the guardrail is opt-out, not opt-in)”
- enabledboolean“Whether the schedule is armed (default true)”
update_scheduled_taskcreates or changes datadescribed as changing data
“Patch a scheduled task's name, prompt, schedule, skip-guard, or enabled state — only the fields passed are changed.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
11 inputs, 1 required
- scheduledTaskIdstringrequired“Scheduled task id to update”
- namestring“Scheduled task name, shown in the console and used in the issue title”
- promptstring“Replaces the issue description verbatim”
- intervalstring“Fire cadence.”
- timestring“24-hour wall-clock time in `timezone`, e.g.”
- timezonestring“IANA timezone id, e.g.”
- weekdaystring“Day of week — required when interval is 'weekly'.”
- dayOfMonthinteger“Day of month, 1-28 — required when interval is 'monthly' (capped at 28 so every month has the day).”
- labelsarray“Tracker label names put on every issue this scheduled task files (replaces the list; [] clears it).”
- skipIfPreviousOpenboolean“Skip a scheduled fire while the previous fire's mission is still open (default true — the guardrail is opt-out, not opt-in)”
- enabledboolean“Set false to pause the schedule without deleting the scheduled task”
run_scheduled_taskruns code or commandsdescribed as changing data
“Fire a scheduled task immediately, bypassing both its schedule and the skip-if-previous-open guard — an explicit run always creates a new issue even while a prior fire's mission is still open.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- scheduledTaskIdstringrequired“Scheduled task id to fire”
list_scheduled_task_runsreads or searches
“Run history for one scheduled task, each row's status (dispatching/dispatched/skipped/failed) and, once its issue exists, the joined mission progress/cost.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- scheduledTaskIdstringrequired“Scheduled task id”
- limitinteger“Runs per page, 1-200 (default 50)”
- cursorstring“nextCursor from the previous page; omit for the newest runs”
delete_scheduled_taskdeletesdescribed as changing data
“Delete a scheduled task and its run history, which no call can bring back.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- scheduledTaskIdstringrequired“Scheduled task id to delete”
list_mcp_serverson 11 other serversreads or searches
“The MCP servers a project's repository declares in its MCP file (.mcp.json by default), each with its binding: enabled roles, transport, status, approved tools, per-role effective tool counts (null w…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- projectIdstringrequired“Project id, e.g.”
list_mcp_bindingsreads or searches
“Every MCP server binding across the projects you can see in your org: project, server, transport, status, enabled roles, how it authenticates, and the NAMES of the credential fields set (never values…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
set_mcp_config_pathcreates or changes datadescribed as changing data
“Point the project at the repository file that declares its MCP servers, e.g.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- projectIdstringrequired“Project id, e.g.”
- configPathstring or nullrequired“Repository-relative path, or null”
bind_mcp_servercreates or changes datadescribed as changing data
“Create or update the binding for a server the repository declares.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
7 inputs, 3 required
- projectIdstringrequired“Project id, e.g.”
- serverNamestringrequired“Server name as the repository's MCP file declares it (see list_mcp_servers)”
- rolesarrayrequired“Every role that may use the server ([] disables it)”
- transportstring“How the gateway reaches the server: 'remote' proxies to remoteUrl, 'isolate' runs the server's npm package away from the sandbox so a secret stays out of it, a…”
- remoteUrlstring“A fixed https URL: a hosted endpoint for a command server, or an override for a URL server”
- credentialobject“Write-only credential the gateway attaches; agents never receive it.”
- approvedToolsarray“The approved subset of the tool snapshot (refresh_mcp_server_tools first).”
unbind_mcp_serverdeletesdescribed as changing data
“Delete a binding and its stored credential: no role receives the server from its next run.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
- projectIdstringrequired“Project id, e.g.”
- serverNamestringrequired“Server name as the repository's MCP file declares it (see list_mcp_servers)”
refresh_mcp_server_toolscreates or changes datadescribed as changing data
“Snapshot the bound server's current tools (with their readOnlyHint / destructiveHint annotations) for approval.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
- projectIdstringrequired“Project id, e.g.”
- serverNamestringrequired“Server name as the repository's MCP file declares it (see list_mcp_servers)”
start_mcp_server_oauthdescribed as changing data
“Begin the OAuth consent for a server bound as remote.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 2 required
- projectIdstringrequired“Project id, e.g.”
- serverNamestringrequired“Server name as the repository's MCP file declares it (see list_mcp_servers)”
- scopestring“Requested scope; defaults to the server's own hint”
- returnTostring“Console path to land on after consent, e.g.”
list_agent_runson 2 other serversreads or searches
“List the agent runs, live and finished, in the caller's accessible projects, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- projectIdstring“Filter to one project id”
- issueIdstring“Only the runs of this mission, by its issue id, e.g.”
- rolestring“Only the runs of this agent role”
- statusstring“Filter by how the run stands: running, completed (finished), stopped (ended on purpose before it finished), failed, or stale (closed without a report)”
- limitinteger“Max results (default 50).”
- cursorstring“nextCursor from the previous page; omit for the newest runs”
get_agent_runon 2 other serversreads or searches
“Fetch one agent run: its run record, metric series (CPU/mem/disk over time), and the agent session summaries (role, outcome, cost, sessionId).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- sandboxIdstringrequired“Agent run id: the run's sandbox id, from list_agent_runs”
get_agent_run_logsreads or searches
“Fetch a session's log content from one agent run.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 3 required
- sandboxIdstringrequired“Agent run id: the run's sandbox id”
- rolestringrequired“Agent role: planner | builder | reviewer | qa”
- sessionIdstringrequired“Session id from get_agent_run's sessions list”
- partstring“Which log stream to read”
watch_agent_runreads or searches
“Wait on one agent run and follow what its agent does, instead of polling get_agent_run.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- sandboxIdstringrequired“Agent run id: the run's sandbox id, from list_agent_runs or get_mission”
- maxSecondsinteger“The longest time to wait, in seconds (default 300, at most 600)”
- sinceinteger“The cursor from an earlier result.”
stop_agent_rundeletesdescribed as changing data
“Stop the agent in one run before it finishes.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- sandboxIdstringrequired“Agent run id: the run's sandbox id, from list_agent_runs”
list_sandbox_templatesreads or searches
“List the org's sandboxes (definitions agents start in), with each one's active version, size and latest build status.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_sandbox_capacityreads or searches
“How many agents the org's missions are running at once against its limit (null while the org is unclassified), which missions wait for an agent slot and why, and whether every slot on the platform is…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- orgIdstring“Required only for a caller in several orgs”
list_sandbox_startersreads or searches
“Ready-made sandbox definitions (Python, Java, Go, Rust, Ruby) to create a sandbox from.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
list_sandbox_template_versionsreads or searches
“Every saved version of a sandbox, newest first, with the active one marked and each one's latest build.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- templateIdstringrequired“Sandbox id (sbt_...)”
get_sandbox_build_logreads or searches
“A page of a build's log after sequence number `after`.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- templateIdstringrequired“Sandbox id (sbt_...)”
- buildIdstringrequired“Build id (tbd_...)”
- afterinteger“Return chunks after this sequence number (default 0)”
save_sandbox_templatecreates or changes datadescribed as changing data
“Create a sandbox (omit templateId) or change one.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs
- templateIdstring“Sandbox id (sbt_...)”
- namestring“Required when creating”
- dockerfilestring“The Dockerfile that builds the sandbox image.”
- starterIdstring“Create from a starter's definition and size”
- sizestring or object“A tier, or { vcpu, memoryMib, diskMb } within 1-4 vCPU, >=3072 MiB per vCPU, <=12288 MiB, 8000-20000 MB”
activate_sandbox_template_versioncreates or changes datadescribed as changing data
“Make a version the one missions use from their next dispatch.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- templateIdstringrequired“Sandbox id (sbt_...)”
- versionIdstringrequired“Version id (stv_...)”
build_sandbox_templatecreates or changes datadescribed as changing data
“Build the sandbox's active version, or return the build already running for it.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- templateIdstringrequired“Sandbox id (sbt_...)”
list_sandbox_registriesreads or searches
“The org's private package registries sandboxes install from: host, auth scheme, username.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
save_sandbox_registrycreates or changes datadescribed as changing data
“Store (or replace) the credential for a registry host.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
4 inputs, 3 required
- hoststringrequired“Registry host or URL, e.g.”
- schemestringrequired“How the registry takes the credential: 'bearer' sends secret as a token, 'basic' sends username and secret”
- usernamestring“Required for basic”
- secretstringrequired“Token or password”
delete_sandbox_templatedeletesdescribed as changing data
“Delete a sandbox with all its versions and builds.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- templateIdstringrequired“Sandbox id (sbt_...)”
delete_sandbox_registrydeletesdescribed as changing data
“Delete the stored credential of a private registry (an id from list_sandbox_registries).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- registryIdstringrequired“Registry credential id, from list_sandbox_registries”
list_environmentson 12 other serversreads or searches
“List per-mission preview environments for the caller's accessible projects.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- issueIdstring“Filter to one issue id”
- projectIdstring“Filter to one project id”
- statusstring“Filter by lifecycle status”
- limitinteger“Max results (default 50).”
get_environmenton 6 other serversreads or searches
“Fetch one preview environment's registry row (status, worker name, timestamps).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- environmentIdstringrequired“Environment id (from list_environments)”
destroy_environmentdeletesdescribed as changing data
“Request teardown of a preview environment (its deployed Worker(s) + every provisioned datastore).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
- environmentIdstringrequired“Environment id to tear down”
list_artifactson 15 other serversreads or searches
“List proof-of-work artifacts (QA screenshots/video/traces) for the caller's accessible projects.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- issueIdstring“Filter to one issue (e.g.”
- projectIdstring“Filter to one project id”
- sandboxIdstring“Filter to ONE agent run's artifacts (e.g.”
- limitinteger“Max results (default 50).”
get_artifacton 22 other serversreads or searches
“Fetch one artifact's metadata + a long-lived signed serving url (open it to view the screenshot/video).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Artifact id (from list_artifacts)”
inspect_missionreads or searches
“Fetch the typed platform-inspection report for a mission, by its issue id.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- issueIdstringrequired“The mission's issue id: a Linear key or a GitHub Issues id, e.g.”
- orgSlugstring“Narrow an ambiguous issue code to one org”
- projectIdstring“Scope to a specific project id”
- sectionsstring“Comma-separated section filter (default all): taskState,retryReason,provenance,…”
list_orgson 5 other serversreads or searches
“List every organization on the platform with its owner email, member count, and pending invite status.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- cursorstring“Opaque page cursor, echoed back as nextCursor by a prior call”
- limitinteger“Page size, 1-100 (API default 50)”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 72 tools
Says what it returns: 82% of 56 tools
States limits, defaults or errors: 14% of 71 tools
Says when to use it: 4% of 72 tools
Items covered per tool: 1.8 of 4 on average

Counted from the listing

Parameters with a description: 100% of 184
Tools with a description: 100% of 72
Typical description length: 303 characters

The tool set

Counted from the listing

Tools: 72
Size of the list: about 21,877 tokens for an agent to load (characters ÷ 4)
Naming: 70 of 72 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 72 of 72 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://mcp.letsship.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "ship": {
      "url": "https://mcp.letsship.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "ship": {
      "type": "http",
      "url": "https://mcp.letsship.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"ship","type":"http","url":"https://mcp.letsship.ai/mcp"}'

Claude Code

claude mcp add --transport http ship https://mcp.letsship.ai/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.letsship.ai/mcp --transport http

Optional settings the entry also lists (left out above): Authorization.
The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint mcp.letsship.ai/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23
Repository github.com/letsship/mcp	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: ai.letsship
GitHub owner: an organization (letsship)

Repository: github.com/letsship/mcp
Stars: 1
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: SECURITY.md

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

5 of 5 record checks met · 4 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 1 star (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.letsship/ship

Answered from the data above

Is ai.letsship/ship safe to install?

We do not rate servers as safe or unsafe. 5 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 38 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does ai.letsship/ship need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has ai.letsship/ship been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can ai.letsship/ship do?

It lists 72 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, send messages, run code or commands and move money. We did not call any tool, so this describes the text, not the behaviour.

Can ai.letsship/ship change or delete data?

38 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does ai.letsship/ship publish a security policy?

Yes: its repository has a public security policy (github.com/letsship/mcp/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.

Where is the source code of ai.letsship/ship?

In github.com/letsship/mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.kivanccakmak/yaverYaveralso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searches, sends messagescompare with this one
io.github.yaver-io/yaverYaveralso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searches, sends messagescompare with this one
ai.rokha/rokhaRokhaalso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searches, sends messagescompare with this one
io.github.keefng8/homeshed-mcpHomeShedalso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searches, sends messagescompare with this one
io.github.callstack/agent-deviceagent-devicealso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one
io.github.A9T9/uivision-mcpUi.Vision MCPalso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one

Active servers whose topic is also “developer-tools” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 3

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
752 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 72 tools, 0 resources, 0 prompts.
3,543 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

developer-tools

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

No value: the AI answer was held back because the quoted text did not clearly support it.

Programming language

not stated

GitHub detects no source language in this repository (docs-only or empty)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

owner: an organization · repository age: 0–30 days · stars: 0–9

api.github.com · 2026-10-22

Maintenance

active

api.github.com · 2026-10-22

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.letsship/ship: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.letsship/ship

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.letsship/ship)](https://protocolprobe.com/mcp/servers/ai.letsship/ship)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology