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
install huqan via npm global
npm install -g huqan
Check that it works
huqan --version 2>&1; echo EXIT:$?
node --versionThe 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-mcpJSON 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 runTested
How to use it
- Start the MCP server with
huqan-mcpfrom your MCP client. - Call the
huqan.policytool with the tool name, the input command and the goal, for example{"tool":"bash","input":"<command>","goal":"<your goal>"}. - Read the returned policy decision before letting the agent run the action.
- Start the MCP server with
- Record decisions as verifiable Trust ReceiptsNot shown working
- Hold changing actions for human approvalNot tested
How far pickfit got
Linux x86_64
- Installs
- Connects
- 1 of 3 features work
- 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.