Toolwork

org.toolworkPublished by toolwork.orgOfficial publisherv0.2.1Updated Nov 5, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

A remote MCP server that lets an assistant search for tools, APIs, SDKs, CLIs or MCP servers matching a task and get a paste-ready setup snippet.

What you can do
  • Search for tools by describing a task in plain words and get one best pick with a paste-ready snippet (MCP client config, install command, or API base URL plus docs)
  • Look up a full Agent Tool Card for a given tool ID, covering capabilities, endpoints, per-client install, auth, side effects, human steps, blockers, pricing and health
  • Report back on whether a suggested tool worked, partially worked or failed, using a report token from a search
  • Call additional tools such as resolve_tool, compare_tools, watch_tools, tell_us and community by name on the full profile
When to use it
Useful when the assistant needs a capability it does not have yet and you want a quick, curated suggestion for an API, SDK, CLI or MCP server, including how to wire it up. It is a discovery and setup aid rather than a tool that performs the task itself.
Requirements
Remote streamable HTTP endpoint; no package install. Reads are free and need no API key. Stateless plain JSON, no session ID required.
Before you install
The server returns third-party tools and setup snippets, so review what a suggested tool does, its auth needs, pricing and side effects before installing or running it. The optional report call sends usage outcome feedback tied to a report token, which feeds rankings.

Installation

In SourceWeft

  1. Open Toolwork in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/org.toolwork%2Ftoolwork/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

3

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 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.

Parametersjobrequiredstageclientagent_typeconstraintswatcher_key

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.

Parametersidrequiredstageclientagent_type

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.

Parameterskindnotestageclientoutcometool_idverdictused_toolagent_typereport_tokenrequiredexpected_toolcontributor_key

Version history

2
  1. v0.2.1LatestNov 5, 2026
  2. v0.2.0Oct 30, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.