pickfit

BrowseMCP servers

天枢编排 MCP tianshu-mcp

Orchestrates external AI agents and verifies results with runtime evidence, auto-reworking on failure.

Use it

Before you install: known vulnerabilities

pickfit found 7 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • npm:basic-ftp 5.3.1 basic-ftp: Quadratic-time CPU denial of service in Client.list() Unix directory-listing parser (RE_LINE backtracking) (GHSA-c475-qrg2-pj4r, high, fixed in 6.2.1)
  • npm:extract-zip 2.0.1 extract-zip allows arbitrary file writes through symlink archive entries (GHSA-7pqw-9j4j-h8q3, high, no fix yet)
See 5 more

Linux x86_64

You need first

  • Runtimes: Node.js >=20
  1. install tianshu-mcp globally via npm

    npm install -g tianshu-mcp

Add it to your agent

claude mcp add tianshu-mcp -- tianshu-mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "tianshu-mcp": {
      "command": "tianshu-mcp",
      "args": []
    }
  }
}

Add tianshu-mcp as an MCP server in your MCP client, then call its tools such as query_info or run_task from the client.

What it does

  • Check that work is done using runtime evidence
    How to use it
    1. Connect tianshu-mcp to your MCP client.
    2. Call the verify_task tool with projectPath set to <your project folder>.
    3. Read the text report it returns.
    Tested
  • Send tasks to external AI agents
    Not tested
  • Redo failed tasks automatically
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 1 of 3 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.9.7

An MCP client handshake over stdio listed 8 tools, and a call to query_info returned a result.

Differences the test machine hit

  • README: npx -y tianshu-mcp
    In the test: npm install -g tianshu-mcp then launch as `tianshu-mcp` (on PATH via ~/.local/bin) so replay works with network off
  • README: binary behaves like a normal CLI
    In the test: tianshu-mcp is a stdio-only MCP server: --help/--version start the server and wait on stdin instead of printing; use the MCP probe handshake instead
  • README: verify_task verifies completion
    In the test: verify_task on a git repo with zero net changes returns tools/call ok with [FAIL] fail-closed verdict plus report path, not a pass

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.