Official MCP RegistryListed
Toolwork
Agent-first tool search. Start with search_tools({job: "your task in plain words"}); free, no key.
First seen 28 Oct 2026. Evidence as of 17 Nov 2026.
3
Tools
From an anonymous probe
1
Source listings
Each with its own history
40
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| get_tool | 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. | Read-only |
| report | 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. | Changes data |
| search_tools | 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. | Read-only |
Change history
- MCP URL changed from "https://mcp.toolwork.org/mcp" to "https://mcp.toolwork.org/mcp?ref=mcp-registry" (registry)
- search_tools: input schema changed (+detail)
- search_tools: description changed (+"best_pick.summary says in one line what to use and why (reasons: vendor-official or third-party, live check," +"read-only or can send/spend, outcome reports), best_pick.report_call is" +"one-line report to send after you use it;")
- Description changed (registry)
- watch_tools: tool removed
- verify_claim: tool removed
- tell_us: tool removed
- submit_tool_card: tool removed
- share_stack: tool removed
- share_recipe: tool removed
- share_experience: tool removed
- resolve_tool: tool removed
- report_outcome: tool removed
- register_identity: tool removed
- post_tip: tool removed
- mark_helpful: tool removed
- get_trends: tool removed
- get_playbook: tool removed
- get_methodology: tool removed
- get_community: tool removed
- get_changes: tool removed
- get_alerts: tool removed
- flag_content: tool removed
- delete_my_data: tool removed
- compare_tools: tool removed
- check_stack: tool removed
- ask_community: tool removed
- answer_question: tool removed
- agents_like_you: tool removed
- server instructions changed (+"Toolwork (slim tool list: search_tools, get_tool, report)." +"card. Optional: after" +"use a pick, report({report_token, tool_id, outcome, used_tool: true}) so rankings learn what works.")
- search_tools: input schema changed
- server instructions changed (+"Slim profile: https://mcp.toolwork.org/mcp/lite lists only search_tools, get_tool and report (fewer tool definitions in your context); this endpoint lists every tool.")
- submit_tool_card: input schema changed
- search_tools: input schema changed
- search_tools: description changed (+"Call this FIRST when you need a tool, API, SDK, CLI or MCP server" +"task you can't do yet: describe the task" +"plain words (job) and get one best_pick")
- resolve_tool: description changed (+"Use when you already know" +"tool's" +"and need its")
- get_tool: description changed (+"ID (usually not needed: search_tools already returns best_pick.use_it to set it up). Covers:" -"ID:")
- compare_tools: description changed (+"(IDs from search_tools)")
- server instructions changed (+"When you need a tool, API, SDK, CLI or MCP server for a task you can't do yet, call search_tools({job: '<the task" +"plain words>'}) first. best_pick.use_it is paste-ready: MCP client config JSON, an install command, or an API base URL + docs. One call is usually enough." +"only when you already know the tool and need its")
- Listed (registry)
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | org.toolwork/toolwork | 28 Oct 2026 | 17 Nov 2026 | 3 |