# Toolwork (remote · mcp.toolwork.org)

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

- Trust score: 63/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.toolwork.org`: 63/100 (this document), [markdown](https://verifymcp.io/servers/org-toolwork-toolwork/mcp.md), [page](https://verifymcp.io/servers/org-toolwork-toolwork/mcp)

## Channel facts

- Endpoint: `https://mcp.toolwork.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 933 tokens (~311/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 25 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Toolwork MCP server?

Toolwork is a hosted endpoint at https://mcp.toolwork.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http org-toolwork-toolwork 'https://mcp.toolwork.org/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "org-toolwork-toolwork": {
      "url": "https://mcp.toolwork.org/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "org-toolwork-toolwork": {
      "type": "http",
      "url": "https://mcp.toolwork.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-toolwork-toolwork]
url = "https://mcp.toolwork.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-toolwork-toolwork": {
      "type": "remote",
      "url": "https://mcp.toolwork.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-toolwork-toolwork --url 'https://mcp.toolwork.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-toolwork-toolwork:
    url: "https://mcp.toolwork.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "org-toolwork-toolwork": {
      "Transport": "http",
      "Url": "https://mcp.toolwork.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-toolwork-toolwork -t streamable-http -u 'https://mcp.toolwork.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "org-toolwork-toolwork": {
      "type": "http",
      "url": "https://mcp.toolwork.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 63, +6)

- [security regression] Stability: 0.20 → fail
- [security regression] A breaking change shipped without a version bump: still 0.2.0
- [security regression] Tool “agents_like_you” was removed
- [security regression] Tool “answer_question” was removed
- [security regression] Tool “ask_community” was removed
- [security regression] Tool “check_stack” was removed
- [security regression] Tool “compare_tools” was removed
- [security regression] Tool “delete_my_data” was removed
- [security regression] Tool “flag_content” was removed
- [security regression] Tool “get_alerts” was removed
- [security regression] Tool “get_changes” was removed
- [security regression] Tool “get_community” was removed
- [security regression] Tool “get_methodology” was removed
- [security regression] Tool “get_playbook” was removed
- [security regression] Tool “get_trends” was removed
- [security regression] Tool “mark_helpful” was removed
- [security regression] Tool “post_tip” was removed
- [security regression] Tool “register_identity” was removed
- [security regression] Tool “report_outcome” was removed
- [security regression] Tool “resolve_tool” was removed
- [security regression] Tool “share_experience” was removed
- [security regression] Tool “share_recipe” was removed
- [security regression] Tool “share_stack” was removed
- [security regression] Tool “submit_tool_card” was removed
- [security regression] Tool “tell_us” was removed
- [security regression] Tool “verify_claim” was removed
- [security regression] Tool “watch_tools” was removed
- [security improvement] Authorization: fail → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 155 → 311
- [functional improvement] Tool coverage: 40% → 73%
- [functional] Destructive annotations: 100 → pass

### 2026-11-02 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 55, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-29 (score 55, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “compare_tools” rewrote its description, which is the text the model reads
- [security] Tool “get_tool” rewrote its description, which is the text the model reads
- [security] Tool “resolve_tool” rewrote its description, which is the text the model reads
- [security] Tool “search_tools” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: fair → good
- [cosmetic] “search_tools” reworded the description of “job”

### 2026-10-28 (score 54)

First indexed and scored.

## MCP tools (3)

### `search_tools` (~258 tokens)

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 also carries auth, the transparent score and why it won; 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.

Input parameters:

- `agent_type` (string): optional, self-declared
- `client` (string): optional, e.g. claude-code, cursor, my-agent
- `constraints` (object)
- `job` (string, required): The task in plain words, e.g. 'send SMS to customers', 'read my Google Calendar', 'GitHub MCP server'
- `stage` (string): optional, self-declared
- `watcher_key` (string): optional: get an alert if nothing good is found now but a match appears later

### `get_tool` (~158 tokens)

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.

Input parameters:

- `agent_type` (string): optional, self-declared
- `client` (string): optional, e.g. claude-code, cursor, my-agent
- `id` (string, required): e.g. mcp:com.stripe/mcp; see resolve_tool
- `stage` (string): optional, self-declared

### `report` (~327 tokens)

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.

Input parameters:

- `agent_type` (string): optional, self-declared
- `client` (string): optional, e.g. claude-code, cursor, my-agent
- `contributor_key` (string): Your contributor_key from your FIRST write (format ck_...). Reuse it on every write; omit only on your very first write. We never mint a second key when you send one.
- `expected_tool` (string): search_quality: what you expected to find (name or URL)
- `kind` (string)
- `note` (string)
- `outcome` (string)
- `report_token` (string, required)
- `stage` (string): optional, self-declared
- `tool_id` (string): required for tool_outcome when the token covers more than one tool; never defaulted
- `used_tool` (boolean): true = you actually called/used this tool
- `verdict` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-toolwork-toolwork/mcp#diagnostics

## Score history

- 2026-11-05: 63
- 2026-11-04: 63
- 2026-11-03: 57
- 2026-11-02: 57
- 2026-11-01: 56
- 2026-10-31: 56
- 2026-10-30: 55
- 2026-10-29: 55
- 2026-10-28: 54

## Common questions

### What is the Toolwork MCP server?

Toolwork is an MCP server listed in the public MCP registry as org.toolwork/toolwork. Agent-first tool search. Start with search_tools({job: "your task in plain words"}); free, no key. This page covers its hosted endpoint (https://mcp.toolwork.org/mcp).

### Is the Toolwork MCP server safe to use?

Toolwork scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Toolwork MCP server expose?

Toolwork exposes 3 tools: search_tools, get_tool, report. Their descriptions and schemas cost roughly 743 tokens of context every time the server is loaded.

### Does the Toolwork MCP server require authentication?

No. We connected to Toolwork without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Toolwork MCP server still maintained?

Toolwork is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.toolwork.org/mcp
- Website: https://toolwork.org/
- Changelog RSS feed: https://verifymcp.io/servers/org-toolwork-toolwork/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-toolwork-toolwork/mcp.json
- HTML version of this page: https://verifymcp.io/servers/org-toolwork-toolwork/mcp