MCP servers › io.github.teamshift-io › sandbox-mcp

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

io.github.teamshift-io/sandbox-mcp

Mock small-business CRM, inbox, calendar, invoicing and phone tools for testing AI agents safely. — the publisher's description

8 of 9 record checks metRead-only · tools listed 2026-10-23version 0.1.0TypeScriptApache-2.0standard input/output46 tools

Summary

io.github.teamshift-io/sandbox-mcp is a local MCP server listed in the official MCP registry at version 0.1.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 46 tools, 2 resources and 0 prompts.

Record checks

8 of 9 record checks met

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)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#8,317 of 15,112 packages by monthly downloads, tied with 13 others
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: npm · listed version current
License: Apache-2.0
Dependencies: no known high or critical advisories
Repository: public
Tools: 46
Described as changing data: 22 of 46 toolsAI-classified
Mainly works on: files and code on the machine it runs on; accounts and data in outside web services; email, chat or social accountsAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

22 tools are described as changing something (crm_create_contact, crm_update_contact, crm_merge_contacts, …): 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: 0.1.0, published 2026-10-04 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-04 (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 0.1.0 (published 2026-10-04).

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

46tools

2resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services; email, chat or social accounts.

22 of 46 tools are described as changing something (creating, editing, deleting, sending or running). For 6 the reading was uncertain, so no mark is shown.

crm_search_contactsreads or searches
“Find people by name, email, phone digits or title.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- querystring
- customerIdstring
- missingInfoboolean
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_get_contactreads or searches
“Full profile of one contact plus their customer account, leads, deals and recent calls.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- contactIdstringrequired“Contact id”
crm_create_contactcreates or changes datadescribed as changing data
“Add a new person, optionally linked to a customer account.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 2 required
- customerIdstring or null
- firstNamestringrequired
- lastNamestringrequired
- emailstring or null
- phonestring or null
- titlestring or null
crm_update_contactcreates or changes datadescribed as changing data
“Change a contact's name, email, phone, title or customer link.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
7 inputs, 1 required
- contactIdstringrequired“Contact id”
- customerIdstring or null
- firstNamestring
- lastNamestring
- emailstring or null
- phonestring or null
- titlestring or null
crm_merge_contactsdeletesdescribed as changing data
“Fold a duplicate contact (mergeId) into the one to keep (keepId): empty fields are filled from the duplicate, all leads/deals/messages/calls are re-pointed, and the duplicate is deleted.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
2 inputs, 2 required
- keepIdstringrequired“Contact to keep id”
- mergeIdstringrequired“Duplicate contact to remove id”
crm_list_customersreads or searches
“List customer accounts (households or businesses), newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- querystring
- statusstring
- ownerIdstring
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_get_customerreads or searches
“One customer account with its contacts, deals, jobs and invoices.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- customerIdstringrequired“Customer id”
crm_list_employeesreads or searches
“Active staff with ids and roles.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- includeInactiveboolean
crm_list_leadsreads or searches
“Inbound leads, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- statusstring
- ownerIdstring
- contactIdstring
- uncontactedboolean
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_update_leadon 1 other servercreates or changes datadescribed as changing data
“Change a lead's status or owner.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
- leadIdstringrequired“Lead id”
- statusstring
- ownerIdstring or null
crm_list_dealsreads or searches
“Sales pipeline deals, most recently updated first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs
- stagestring
- ownerIdstring
- customerIdstring
- contactIdstring
- openOnlyboolean
- staleDaysinteger
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_get_dealreads or searches
“One deal with its quotes and contact.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- dealIdstringrequired“Deal id”

Show 34 more tools

crm_update_dealcreates or changes datadescribed as changing data
“Move a deal to a new stage and/or set its next action, amount or owner.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 1 required
- dealIdstringrequired“Deal id”
- stagestring
- lostReasonstring
- nextActionobject or null
- amountCentsinteger“Deal value in integer cents, e.g.”
- ownerIdstring or null
crm_list_quotesreads or searches
“Quotes/estimates.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- statusstring
- dealIdstring
- customerIdstring
- notFollowedUpboolean
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_send_quotecreates or changes datadescribed as changing data
“Send a draft quote to the customer (status becomes sent).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
- quoteIdstringrequired“Quote id”
- expiresOnstring“Date, YYYY-MM-DD”
crm_follow_up_quotesends messagesdescribed as changing data
“Message the deal's contact about a sent/viewed quote and record the follow-up on the quote.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 2 required
- quoteIdstringrequired“Quote id”
- bodystringrequired
- channelstring“Default email”
- contactIdstring“Defaults to the deal's contact”
- employeeIdstring“Sender; defaults to the company address”
crm_list_tasksreads or searches
“To-dos for staff.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- statusstring
- assigneeIdstring
- relatedIdstring
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
crm_create_taskcreates or changes datadescribed as changing data
“Create a to-do for a staff member, linked to the records it is about (relatedIds).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
- titlestringrequired
- assigneeIdstring or null
- dueOnstring or null
- relatedIdsarray
crm_complete_taskcreates or changes datadescribed as changing data
“Mark an open task done.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- taskIdstringrequired“Task id”
inbox_list_threadsreads or searches
“Email and SMS conversations, newest activity first, with unread counts and the last message snippet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- channelstring
- contactIdstring
- unreadOnlyboolean
- querystring
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
inbox_get_threadreads or searches
“All messages in one thread, oldest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- threadIdstringrequired“Thread (thr_…) id”
inbox_send_emailsends messagesdescribed as changing data
“Send an email to a contact, raw address, or as a reply in an existing thread (threadId).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 1 required
- contactIdstring
- toarray
- threadIdstring
- subjectstring
- bodystringrequired
- employeeIdstring“Sender; defaults to the company address”
- relatedIdsarray“Records this email is about”
inbox_send_smssends messagesdescribed as changing data
“Send a text message to a contact, raw number, or within an SMS thread.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 1 required
- contactIdstring
- tostring
- threadIdstring
- bodystringrequired
- employeeIdstring
- relatedIdsarray
inbox_mark_thread_readcreates or changes datadescribed as changing data
“Mark every message in a thread as read after handling it.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- threadIdstringrequired“Thread id”
calendar_list_jobsreads or searches
“Scheduled work (appointments / work orders / projects), latest start first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- statusstring
- customerIdstring
- assigneeIdstring
- fromstring“Inclusive; YYYY-MM-DD or datetime”
- tostring“Exclusive; YYYY-MM-DD or datetime”
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
calendar_get_jobreads or searches
“One job with its customer and invoices.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- jobIdstringrequired“Job id”
calendar_schedule_jobcreates or changes datadescribed as changing data
“Book new work for a customer.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
8 inputs, 4 required
- customerIdstringrequired“Customer id”
- titlestringrequired
- scheduledStartstringrequired“ISO-8601 datetime, e.g.”
- scheduledEndstringrequired“ISO-8601 datetime, e.g.”
- assigneeIdsarray
- quoteIdstring or null
- notesstring or null
- allowOverlapboolean
calendar_reschedule_jobcreates or changes datadescribed as changing data
“Move a scheduled or no-show job to a new time window (optionally new assignees).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 3 required
- jobIdstringrequired“Job id”
- scheduledStartstringrequired“ISO-8601 datetime, e.g.”
- scheduledEndstringrequired“ISO-8601 datetime, e.g.”
- assigneeIdsarray
- reasonstring
- allowOverlapboolean
calendar_cancel_jobdeletesdescribed as changing data
“Cancel a scheduled or in-progress job.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
2 inputs, 2 required
- jobIdstringrequired“Job id”
- reasonstringrequired
calendar_complete_jobcreates or changes datadescribed as changing data
“Mark a scheduled or in-progress job completed now, with optional notes.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
- jobIdstringrequired“Job id”
- notesstring
invoicing_list_invoicesreads or searches
“Invoices, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- statusstring
- customerIdstring
- jobIdstring
- overdueboolean
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
invoicing_get_invoicereads or searches
“One invoice with its payments and balance due.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- invoiceIdstringrequired“Invoice id”
invoicing_create_invoicecreates or changes datadescribed as changing data
“Issue an invoice to a customer (optionally for a job of that customer).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 2 required
- customerIdstringrequired“Customer id”
- jobIdstring or null
- lineItemsarrayrequired
- issuedOnstring“Date, YYYY-MM-DD”
- dueOnstring“Date, YYYY-MM-DD”
invoicing_send_remindersends messagesdescribed as changing data
“Send a payment reminder for an open or partially-paid invoice to the customer's contact (outbox only).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 1 required
- invoiceIdstringrequired“Invoice id”
- channelstring
- bodystring
- contactIdstring
- employeeIdstring
invoicing_void_invoicedeletesdescribed as changing data
“Void an invoice that has no payments applied (e.g.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
2 inputs, 2 required
- invoiceIdstringrequired“Invoice id”
- reasonstringrequired
invoicing_record_paymentcreates or changes datadescribed as changing data
“Record money received against an invoice.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
- invoiceIdstringrequired“Invoice id”
- amountCentsintegerrequired“Amount received in integer cents, e.g.”
- methodstringrequired
- referencestring
invoicing_list_paymentsreads or searches
“Payments received, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- invoiceIdstring
- customerIdstring
- unmatchedboolean
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
invoicing_match_paymentcreates or changes datadescribed as changing data
“Apply an unmatched payment to the invoice it pays.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 2 required
- paymentIdstringrequired“Payment id”
- invoiceIdstringrequired“Invoice id”
phone_list_callsreads or searches
“Phone call log, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- directionstring
- outcomestring
- contactIdstring
- sincestring“Inclusive; YYYY-MM-DD or datetime”
- offsetinteger“Rows to skip (default 0).”
- limitinteger“Max rows to return (default 25, max 100).”
phone_log_callcreates or changes datadescribed as changing data
“Record a call you made or took (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 1 required
- contactIdstring
- phonestring“Defaults to the contact's phone”
- directionstring“Default outbound”
- outcomestringrequired
- durationSecinteger
- summarystring or null
- employeeIdstring
admin_get_company_policies
“The company's plain-language operating rules (response times, follow-up cadence, payment terms...).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
admin_get_company
“Company profile plus the simulated current time and today's date in company time.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
admin_get_audit_log
“Every mutation attempted so far (tool, input, ok/error, changed ids), in order.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- sinceSeqinteger
admin_reset
“Restore the original dataset and clock, discarding every change.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
Takes no inputs.
admin_save_state
“Write the current dataset, audit log and outbox to the --state-out file for grading.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
Takes no inputs.
admin_advance_clock
“Move simulated time forward by N minutes (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- minutesintegerrequired

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 40 tools
Says what it returns: 100% of 18 tools
States limits, defaults or errors: 28% of 40 tools
Says when to use it: 100% of 9 tools
Items covered per tool: 3.5 of 4 on average

Counted from the listing

Parameters with a description: 40% of 167
Tools with a description: 100% of 46
Typical description length: 113 characters

The tool set

Counted from the listing

Tools: 46
Size of the list: about 8,122 tokens for an agent to load (characters ÷ 4)
Naming: 46 of 46 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 40 of 46 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 npm package @teamshift/sandbox-mcp

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": {
    "sandbox-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@teamshift/sandbox-mcp@0.1.0",
        "--industry",
        "home-services",
        "--seed",
        "42"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "sandbox-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@teamshift/sandbox-mcp@0.1.0",
        "--industry",
        "home-services",
        "--seed",
        "42"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "sandbox-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@teamshift/sandbox-mcp@0.1.0",
        "--industry",
        "home-services",
        "--seed",
        "42"
      ]
    }
  }
}

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

code --add-mcp '{"name":"sandbox-mcp","type":"stdio","command":"npx","args":["-y","@teamshift/sandbox-mcp@0.1.0","--industry","home-services","--seed","42"]}'

Claude Code

claude mcp add --transport stdio sandbox-mcp -- npx -y @teamshift/sandbox-mcp@0.1.0 --industry home-services --seed 42

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

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y @teamshift/sandbox-mcp@0.1.0 --industry home-services --seed 42

Optional arguments the entry also lists (left out above): --toolsets.
Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
This runs the publisher's code on your machine (npx). 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: 0.1.0
Latest stable: 0.1.0
Status: current
Withdrawn: no

Source: registry.npmjs.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 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-uHNUJn0oSC4t20Cea…
Signature: signed
License: Apache-2.0

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

Usage

Downloads: 255 in the last month

Source: api.npmjs.org · 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 0.1.0 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/teamshift-io/smb-sandbox	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.teamshift-io
GitHub owner: an organization (teamshift-io)
Build record: signed

Repository: github.com/teamshift-io/smb-sandbox
Stars: 0
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 · 2026-10-23; 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

8 of 9 record checks met

#8,317 of 15,112 packages by monthly downloads, tied with 13 others
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.
MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
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.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build 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.teamshift-io/sandbox-mcp

Answered from the data above

Is io.github.teamshift-io/sandbox-mcp safe to install?

We do not rate servers as safe or unsafe. 8 of its 9 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. 22 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.teamshift-io/sandbox-mcp been security tested?

Partly. 3 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.teamshift-io/sandbox-mcp do?

It lists 46 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 and send messages. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.teamshift-io/sandbox-mcp change or delete data?

22 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.teamshift-io/sandbox-mcp publish a security policy?

Yes: its repository has a public security policy (github.com/teamshift-io/smb-sandbox/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.

Is the listed version current?

Yes. The registry lists 0.1.0, the latest stable release on npm.

Where is the source code of io.github.teamshift-io/sandbox-mcp?

In github.com/teamshift-io/smb-sandbox, 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.

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: exercised
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

3 exercised9 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). 3 of the 12 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
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised

Not run, with the reason · 9

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

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)
8,409 msConnected after 0 redirects.
Read the inventory: 46 tools, 2 resources, 0 prompts.
10,352 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

no value

No value: the two AI models (Gemini and Claude) disagreed, so neither answer is shown.

Pricing modelAI-classified

no value

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

Programming language

TypeScript

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

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

npm

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 (sri)

package registry · 2026-10-23

Signature / provenance

signed

package registry · 2026-10-23

Dependency advisories

none known

npm audit · 2026-10-23

Popularity

255 downloads a month

package registry · 2026-10-23

Publisher signals

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

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.teamshift-io/sandbox-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.teamshift-io/sandbox-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.teamshift-io/sandbox-mcp)](https://protocolprobe.com/mcp/servers/io.github.teamshift-io/sandbox-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