Skip to content

Toolwork MCP server

org.toolwork/toolworktoolwork.orgstreamable-httpv0.2.2Scanned

Agent-first tool search. Start with search_tools({job: "your task in plain words"}); free, no key.

3 tools: 2 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Toolwork MCP server can do

The Toolwork MCP server is published by toolwork.org, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: search_tools and report), but cannot delete data. 1 tool only reads.

1 tool reads private data (search_tools); 1 tool brings in text other people can write (search_tools).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 17, 2026, version 0.2.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

3 tools

Changes things 2Claude Code: ask
  • reportPREFERRED way to give feedback, using the top-level report_token from search_tools/get_tool/compare_tools (covers the first 10 results, valid 30 days).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    PREFERRED way to give feedback, using the top-level report_token from search_tools/get_tool/compare_tools (covers the first 10 results, valid 30 days). Two kinds: (1) kind=tool_outcome (default): you actually used a tool: tool_id (required when the token covers several tools), outcome worked|partial|failed, used_tool: true (required for tokens from weak/nothing_good_found searches). (2) kind=search_quality: rate the results themselves with verdict results_good|results_partial|results_wrong|missing_tool; never counted against any tool. Note max 300 chars. Reuse your contributor_key.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • search_toolsCall this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_i…Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "search_tools" says "search": a word for reading.
    • The description's first verb is "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • private-dataThe description's first sentence says "doc": it reads documents.
    • untrusted-inputThe description's first sentence says "call" and "url": it reads web pages, which anyone can write.

    Findings

    • Warn

      The server marks "search_tools" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_tools" says "search": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Call this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_it snippet (MCP client config JSON, install command, or API base URL + docs). One call is usually enough: best_pick.summary says in one line what to use and why (reasons: vendor-official or third-party, live check, auth, read-only or can send/spend, outcome reports), best_pick.report_call is the one-line report to send after you use it; results lists ranked alternatives with score breakdowns (evidence, source URL, date), side effects and human steps; verdict is honest (good_match / weak_matches / nothing_good_found, then best_pick is null). Free, no key. Returns a top-level report_token for optional feedback.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • get_toolFull Agent Tool Card for one ID (usually not needed: search_tools already returns best_pick.use_it to set it up).No findings

    Why it is in this group

    • The name "get_tool" says "get": a word for reading.
    Description, as the server wrote it
    Full Agent Tool Card for one ID (usually not needed: search_tools already returns best_pick.use_it to set it up). Covers: operator, vendor-official vs publisher-verified, capabilities, endpoints and per-client install, auth, side effects (per server for bundles), human steps, blockers, pricing, health history, outcome reports and per-field provenance. Unknown IDs return isError with error_code not_found.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:24 UTC, unchanged since Nov 19, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.toolwork.org/mcp?ref=mcp-registry: tools/list returned 3 tools to an anonymous client, including search_tools (write), report (write)

    What this check looks for

Posture changes

  1. Nov 5, 2026
    • Tools that change things, listed without credentials: 18 to 2

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "search_tools" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_tools" says "search": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 changed.~1 changedView diff
  2. Tools25 removed, 2 changed.−25 removed~2 changedView diff
    • Removed:agents_like_you
    • Removed:answer_question
    • Removed:ask_community
    • Removed:check_stack
    • Removed:compare_tools
    • Removed:delete_my_data
    • Removed:flag_content
    • Removed:get_alerts
    • Removed:get_changes
    • Removed:get_community
    • Removed:get_methodology
    • Removed:get_playbook
    • Removed:get_trends
    • Removed:mark_helpful
    • Removed:post_tip
    • Removed:register_identity
    • Removed:report_outcome
    • Removed:resolve_tool
    • Removed:share_experience
    • Removed:share_recipe
    • Removed:share_stack
    • Removed:submit_tool_card
    • Removed:tell_us
    • Removed:verify_claim
    • Removed:watch_tools
    • Changed:get_toolOnly readsdescription
    • Changed:search_toolsChanges thingsdescriptioninputSchema
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 18 -> 2.View diff
    • Tools that change things, listed without credentials: 18 to 2

Install

Pinned to version 0.2.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http toolwork https://mcp.toolwork.org/mcp?ref=mcp-registry
claude mcp add --transport http toolwork https://mcp.toolwork.org/mcp?ref=mcp-registry

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__toolwork__get_tool"
    ],
    "ask": [
      "mcp__toolwork__search_tools",
      "mcp__toolwork__report"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as toolwork. Review it before you use it.

Capability tags behind 1 rule
  • mcp__toolwork__search_tools private-data, untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/org.toolwork/toolwork/verify?hash=34e67b4004c01f25b5d3fec368027fa9b63948c96e7e9c2180563f400c4e5b56" | jq -e '.changed == false'

Pinned hash 34e67b4004c0, from Nov 17, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/org.toolwork/toolwork/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for org.toolwork/toolwork
[![Anlyon Radar](https://radar.anlyon.com/badge/org.toolwork/toolwork.svg)](https://radar.anlyon.com/servers/org.toolwork/toolwork)

Source: MCP Registry. Synced Nov 17, 2026, 13:18 UTC.

Toolwork MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Toolwork MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Toolwork MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Toolwork MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Toolwork MCP server have?

3 tools: 2 write, 1 read. search_tools, report and get_tool.

Does the Toolwork MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Toolwork MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Toolwork MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.