pickfit

BrowseMCP servers

HUQAN

Local-first gate that blocks or holds risky AI agent actions and records verifiable Trust Receipts.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js 22.13.0 or newer
  1. install huqan via npm global

    npm install -g huqan

Check that it works

huqan --version 2>&1; echo EXIT:$?
node --version

The output should contain “1.1.1”.

Add it to your agent

claude mcp add huqan -e HUQAN_MCP_OPERATOR_TOKEN='<HUQAN_MCP_OPERATOR_TOKEN>' -- huqan-mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "huqan": {
      "command": "huqan-mcp",
      "args": [],
      "env": {
        "HUQAN_MCP_OPERATOR_TOKEN": "<HUQAN_MCP_OPERATOR_TOKEN>"
      }
    }
  }
}

You fill in

  • HUQAN_MCP_OPERATOR_TOKEN: operator tools require token (required)

Ask the user for HUQAN_MCP_OPERATOR_TOKEN; pickfit never had a value, so these are placeholders.

Add huqan-mcp as an MCP server in your MCP client, then call its tools from there.

What it does

  • Block risky agent actions before they run
    How to use it
    1. Start the MCP server with huqan-mcp from your MCP client.
    2. Call the huqan.policy tool with the tool name, the input command and the goal, for example {"tool":"bash","input":"<command>","goal":"<your goal>"}.
    3. Read the returned policy decision before letting the agent run the action.
    Tested
  • Record decisions as verifiable Trust Receipts
    Not shown working
  • Hold changing actions for human approval
    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.

Good for

  • block risky shell and infrastructure actions before execution
  • hold unknown commands for human review
  • record verifiable Trust Receipts for agent decisions

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 31 Oct 2026
  • Version 1.1.1

An MCP client handshake over stdio listed 26 tools, and a call to huqan.policy returned a result.

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.