MCP servers › io.github.Harflow-Dev › harflow-mcp

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

io.github.Harflow-Dev/harflow-mcp

Dispatch coding tasks to local headless agents with persistent history and workflows. — the publisher's description

7 of 8 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedversion 0.0.1PythonApache-2.0standard input/output48 tools

Summary

io.github.Harflow-Dev/harflow-mcp is a local MCP server listed in the official MCP registry at version 0.0.1. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 48 tools, 0 resources and 0 prompts.

Record checks

7 of 8 record checks met · 1 does 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
not met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: no download figure available
Not ranked by stars: 0 stars (ranked from 10)

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

Key facts

Runs: local package
Transport: standard input/output
Package: PyPI · listed version current
License: Apache-2.0
Dependencies: no known high or critical advisories
Repository: public
Tools: 48
Described as changing data: 19 of 48 toolsAI-classified
Mainly works on: files and code on the machine it runs on; cloud accounts, servers or DevOps toolsAI-classified
Topic: developer-toolsAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

19 tools are described as changing something (start_task, respond_approval_request, subscribe, …): our AI model's reading of the descriptions, not something we tested. 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: 0.0.1, published 2026-10-22 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-22 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-23
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 0.0.1 (published 2026-10-22).

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

48tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; cloud accounts, servers or DevOps tools.

19 of 48 tools are described as changing something (creating, editing, deleting, sending or running). For 8 the reading was uncertain, so no mark is shown.

list_backendson 1 other serverreads or searches
“Report the available agent backends, what is installed, and what each can actually do.”
Takes no inputs.
start_taskon 5 other serversruns code or commandsdescribed as changing data
“Dispatch a coding task to a headless agent and return immediately.”
16 inputs, 2 required
- promptstringrequired
- repo_pathstringrequired
- backendstring or null
- freedomstring or null
- modelstring or null
- max_turnsinteger or null
- reasoning_effortstring or null
- networkboolean or null
- caller_approvalsboolean
- interaction_ownerstring
- groupstring or null
- titlestring or null
- workflowstring or null
- auto_continueinteger
- notifystring or null
- extra_writable_pathsarray or null
list_approval_requestson 2 other serversreads or searches
“List bounded permission request metadata for exactly one task or root workflow tree.”
4 inputs
- task_idstring or null
- workflow_run_idstring or null
- cursorstring or null
- limitinteger
get_approval_requeston 2 other serversreads or searches
“Read the complete exact action for an authorized direct caller.”
2 inputs, 2 required
- task_idstringrequired
- request_idstringrequired
respond_approval_requestdoes something elsedescribed as changing data
“Reserve approve/reject for one exact action, with stale/duplicate answer protection.”
6 inputs, 5 required
- task_idstringrequired
- request_idstringrequired
- action_digeststringrequired
- owner_revisionintegerrequired
- decisionstringrequired
- interaction_ownerstring
preview_task_permissionsreads or searches
“Preview standalone task permissions without launching an agent or allocating scratch.”
6 inputs, 1 required
- repo_pathstringrequired
- backendstring or null
- freedomstring or null
- networkboolean or null
- caller_approvalsboolean
- extra_writable_pathsarray or null
subscribeon 263 other serversdoes something elsedescribed as changing data
“Durably subscribe to one task's observed terminal settlement using a configured alias.”
2 inputs, 2 required
- task_idstringrequired
- notifystringrequired
get_task_notificationsreads or searches
“Read bounded subscription delivery states; this never establishes task success.”
1 input, 1 required
- task_idstringrequired
unsubscribeon 244 other serversdoes something elsedescribed as changing data
“Stop future attempts for a task/alias (or all aliases); in-flight requests may finish.”
2 inputs, 1 required
- task_idstringrequired
- notifystring or null
get_task_statuson 13 other serversreads or searches
“Report a dispatched task's current state without blocking.”
3 inputs, 1 required
- task_idstringrequired
- include_tailboolean
- briefboolean
wait_for_taskon 3 other serversreads or searches
“Wait for a task to finish, giving up after a timeout without disturbing the run.”
4 inputs, 1 required
- task_idstringrequired
- timeout_secondsinteger or null
- include_tailboolean
- untilstring
wait_for_tasksreads or searches
“Observe 1..32 unique task IDs, returning compact statuses in requested order.”
4 inputs, 1 required
- task_idsarrayrequired
- modestring
- timeout_secondsinteger or null
- untilstring

Show 36 more tools

continue_taskon 2 other serversruns code or commandsdescribed as changing data
“Start a fresh session from a conclusively settled standalone task.”
3 inputs, 1 required
- task_idstringrequired
- extra_promptstring or null
- notes_pathstring or null
resume_taskon 1 other serverruns code or commandsdescribed as changing data
“Continue a finished task's session with follow-up instructions.”
4 inputs, 1 required
- task_idstringrequired
- followup_promptstring or null
- max_turnsinteger or null
- networkboolean or null
list_taskson 66 other serversreads or searches
“List dispatched tasks, oldest first.”
9 inputs
- statusstring or null
- backendstring or null
- groupstring or null
- title_containsstring or null
- repostring or null
- sincestring or null
- limitinteger or null
- fieldsarray or null
- cursorstring or null
list_task_pagereads or searches
“Stable newest-first persisted task headers; inspect a task for reconciled status/output.”
5 inputs
- limitinteger
- cursorstring or null
- active_onlyboolean
- session_idstring or null
- task_idsarray or null
cancel_taskon 19 other serversdescribed as changing data
“Stop a running task, terminating the agent and any processes it spawned, and cascade the same stop to any live descendants this bridge can find.”
1 input, 1 required
- task_idstringrequired
get_task_eventsreads or searches
“Fetch normalized events from a task's event log.”
5 inputs, 1 required
- task_idstringrequired
- limitinteger
- before_seqinteger or null
- after_seqinteger or null
- kindsarray or null
get_task_event_pagereads or searches
“Read one bounded recent or older activity page using an opaque stable cursor.”
4 inputs, 1 required
- task_idstringrequired
- limitinteger
- cursorstring or null
- kindsarray or null
send_messageon 95 other serverssends messagesdescribed as changing data
“Add a message to a running live-input task, as if the user had typed it mid-run — or queue it for the next continuation of a task that has no live input.”
2 inputs, 2 required
- task_idstringrequired
- textstringrequired
cancel_queued_messagedeletesdescribed as changing data
“Withdraw a follow-up that send_message queued for a task's next continuation.”
2 inputs, 2 required
- task_idstringrequired
- message_idstringrequired
list_workflowson 21 other serversreads or searches
“List inner saved definitions; any incompatible or unavailable source refuses the whole list.”
Takes no inputs.
get_workflowon 20 other serversreads or searches
“Read a saved workflow definition and revision.”
1 input, 1 required
- namestringrequired
save_workflowon 2 other serverscreates or changes datadescribed as changing data
“Validate and save an explicit workflow; expected_revision protects concurrent edits.”
4 inputs, 2 required
- namestringrequired
- definitionobjectrequired
- expected_revisioninteger or null
- expected_workflow_idstring or null
delete_workflowon 5 other serversdeletesdescribed as changing data
“Delete a qualified definition after scanning qualified referrers; historical snapshots remain available.”
1 input, 1 required
- namestringrequired
workflow_buildergenerates contentdescribed as changing data
“Generate a workflow, or refine the current canvas into an unsaved validated proposal.”
7 inputs, 2 required
- namestringrequired
- promptstringrequired
- repo_pathstring or null
- agentobject or null
- fallbacksarray or null
- definitionobject or null
- sourceobject or null
followup_workflow_buildersends messagesdescribed as changing data
“Queue a message in the same workflow-builder conversation without saving its draft.”
2 inputs, 2 required
- run_idstringrequired
- promptstringrequired
apply_workflow_draftcreates or changes datadescribed as changing data
“Publish a preview from the verified active builder task; never write a saved workflow.”
2 inputs, 2 required
- definitionobjectrequired
- expected_draft_revisionintegerrequired
preview_workflow_runreads or searches
“Preview native ownership, inherited permissions and fallback reasons without launching.”
4 inputs, 2 required
- namestringrequired
- repo_pathstringrequired
- overridesobject or null
- networkboolean or null
start_workflowon 2 other serversruns code or commandsdescribed as changing data
“Start a durable workflow run; returns workflow_run_id rather than task_id.”
10 inputs, 3 required
- namestringrequired
- promptstringrequired
- repo_pathstringrequired
- overridesobject or null
- freedomstring or null
- networkboolean or null
- expected_preview_hashstring or null
- goalstring or null
- notifystring or null
- notify_eventsarray or null
subscribe_workflowdoes something elsedescribed as changing data
“Subscribe a root workflow to configured webhooks (terminal, attention, or both).”
3 inputs, 2 required
- workflow_run_idstringrequired
- notifystringrequired
- eventsarray or null
unsubscribe_workflowdoes something elsedescribed as changing data
“Stop future workflow delivery attempts for one configured alias, or every alias.”
2 inputs, 1 required
- workflow_run_idstringrequired
- notifystring or null
get_workflow_notificationsreads or searches
“Read root workflow subscriptions and at most 50 recent delivery states; direct callers only.”
1 input, 1 required
- workflow_run_idstringrequired
revise_workflow_goalcreates or changes datadescribed as changing data
“Revise a root run goal at a quiescent paused or awaiting-input checkpoint.”
3 inputs, 3 required
- run_idstringrequired
- goalstringrequired
- expected_revisionintegerrequired
list_workflow_runson 3 other serversreads or searches
“List recorded workflow runs.”
2 inputs
- offsetinteger
- limitinteger
list_workflow_run_pagereads or searches
“Stable newest-first run headers, with bounded ancestor/session-owner lookups.”
5 inputs
- limitinteger
- cursorstring or null
- active_onlyboolean
- related_run_idstring or null
- run_idsarray or null
get_workflow_statuson 6 other serversreads or searches
“Read a workflow run's execution state and task associations.”
1 input, 1 required
- workflow_run_idstringrequired
wait_for_workflowreads or searches
“Wait for a workflow run to need attention or finish; read-only and resumable.”
3 inputs, 1 required
- workflow_run_idstringrequired
- timeout_secondsinteger or null
- untilstring
get_workflow_run_detailreads or searches
“Losslessly read executions, decisions, checklist, technical_plan, definition, owner_contracts, builder_draft, generated_definition, question, reason or wait_reason.”
4 inputs, 2 required
- workflow_run_idstringrequired
- viewstringrequired
- cursorstring or null
- limitinteger
pause_workflowdoes something elsedescribed as changing data
“Stop scheduling while active steps settle.”
1 input, 1 required
- workflow_run_idstringrequired
resume_workflow
“Resume a caller-owned run with instructions and optional explicit attempt grants.”
5 inputs, 1 required
- workflow_run_idstringrequired
- instructionsstring or null
- additional_attemptsinteger
- decision_idstring or null
- allow_optional_review_skipboolean
read_workflow_assigned_input
“Read an immutable input explicitly assigned to your active worker activation.”
6 inputs, 2 required
- workflow_run_idstringrequired
- execution_idstringrequired
- source_run_idstring or null
- task_idstring or null
- cursorstring or null
- limitinteger
inspect_workflow_node
“Inspect any fully settled node execution in your workflow, including older executions.”
8 inputs, 2 required
- workflow_run_idstringrequired
- execution_idstringrequired
- task_idstring or null
- viewstring
- cursorstring or null
- limitinteger or null
- before_seqinteger or null
- after_seqinteger or null
recover_workflowon 1 other server
“Explicitly recover a failed settled run; retain completed work and supply a reason.”
3 inputs, 2 required
- workflow_run_idstringrequired
- reasonstringrequired
- additional_attemptsinteger
cancel_workflowon 3 other servers
“Stop root scheduling and cascade cancellation to associated tasks and children.”
1 input, 1 required
- workflow_run_idstringrequired
register_artifacton 1 other server
“Register an existing regular-file metadata reference for the verified calling task.”
3 inputs, 2 required
- pathstringrequired
- kindstringrequired
- notestring
get_task_artifacts
“Page at most 50 artifact references with current stat observations, not content verification.”
3 inputs, 1 required
- task_idstringrequired
- cursorstring or null
- limitinteger
get_workflow_artifacts
“Page artifact references registered by the attempts of a workflow run and its linked child runs.”
5 inputs, 1 required
- workflow_run_idstringrequired
- cursorstring or null
- limitinteger
- execution_idstring or null
- task_idstring or null

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. 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 40 tools
Says what it returns: 65% of 40 tools
States limits, defaults or errors: 31% of 32 tools
Says when to use it: 3% of 40 tools
Items covered per tool: 2.1 of 4 on average

Counted from the listing

Parameters with a description: 0% of 175
Tools with a description: 100% of 48
Typical description length: 1,001 characters

The tool set

Counted from the listing

Tools: 48
Size of the list: about 19,582 tokens for an agent to load (characters ÷ 4)
Naming: 46 of 48 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 40 of 48 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 PyPI package harflow-mcp

Our sandbox started this package 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. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "harflow-mcp": {
      "command": "uvx",
      "args": [
        "harflow-mcp==0.0.1"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "harflow-mcp": {
      "command": "uvx",
      "args": [
        "harflow-mcp==0.0.1"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "harflow-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "harflow-mcp==0.0.1"
      ]
    }
  }
}

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

code --add-mcp '{"name":"harflow-mcp","type":"stdio","command":"uvx","args":["harflow-mcp==0.0.1"]}'

Claude Code

claude mcp add --transport stdio harflow-mcp -- uvx harflow-mcp==0.0.1

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

npx @modelcontextprotocol/inspector@2.11.0 -- uvx harflow-mcp==0.0.1

This runs the publisher's code on your machine (uvx). Read its README first.
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.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 0.0.1
Latest stable: 0.0.1
Status: current
Withdrawn: no

Source: pypi.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (OSV.dev). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha256-926b990e608701aea…
License: Apache-2.0

Source: the package registry · 2026-10-23.

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
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 0.0.1 on PyPI	Exists and can be installed	matches	PyPI · 2026-10-23
Repository github.com/Harflow-Dev/HarflowMCP	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

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

Namespace: io.github.Harflow-Dev
GitHub owner: an organization (Harflow-Dev)

Repository: github.com/Harflow-Dev/HarflowMCP
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; 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

7 of 8 record checks met · 1 does not apply

Not ranked by downloads: no download figure available
Not ranked by stars: 0 stars (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.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierApache-2.0
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. 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 io.github.Harflow-Dev/harflow-mcp

Answered from the data above

Is io.github.Harflow-Dev/harflow-mcp safe to install?

We do not rate servers as safe or unsafe. 7 of its 8 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. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 19 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.

Has io.github.Harflow-Dev/harflow-mcp been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.Harflow-Dev/harflow-mcp do?

It lists 48 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 generate content and more. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.Harflow-Dev/harflow-mcp change or delete data?

19 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 io.github.Harflow-Dev/harflow-mcp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 0.0.1, the latest stable release on PyPI.

Where is the source code of io.github.Harflow-Dev/harflow-mcp?

In github.com/Harflow-Dev/HarflowMCP, 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.IMNMV/clauderClaudeR - RStudio MCP Serveralso has tools that creates or changes data, deletes, runs code or commands, generates content, does something else, reads or searches, sends messagescompare with this one
io.github.kivanccakmak/yaverYaveralso has tools that creates or changes data, deletes, runs code or commands, generates content, does something else, 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, generates content, does something else, reads or searches, sends messagescompare with this one
ai.rokha/rokhaRokhaalso has tools that creates or changes data, deletes, runs code or commands, generates content, does something else, reads or searches, sends messagescompare with this one
io.github.tomyud1/godot-mcpalso has tools that creates or changes data, deletes, runs code or commands, generates content, reads or searches, sends messagescompare with this one
io.github.SummerEngine/summerSummer Enginealso has tools that creates or changes data, deletes, runs code or commands, generates content, does something else, reads or searchescompare 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

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. 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 applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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

Does not apply to this server · 6

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 runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 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 the published package in an isolated sandbox (read-only mode)
4,214 msConnected after 0 redirects.
Read the inventory: 48 tools, 0 resources, 0 prompts.
4,772 msFinished: 2 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

not checked

no website in the registry entry

Programming language

Python

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

prompts, resources, tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

pypi

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sha256)

package registry · 2026-10-23

Signature / provenance

does not apply

PyPI publishes no registry signature or attestation equivalent to npm dist.signatures

Dependency advisories

none known

OSV.dev · 2026-10-23

Popularity

not known (our limit)

Our lookup failed (network error, timeout or rate limit). This is our limit, not the server's.

Publisher signals

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

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

your machine

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. “io.github.Harflow-Dev/harflow-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.Harflow-Dev/harflow-mcp

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/io.github.Harflow-Dev/harflow-mcp)](https://protocolprobe.com/mcp/servers/io.github.Harflow-Dev/harflow-mcp)

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