colt2822/Drex-MCP

MCP server exposing Nace.AI Drex as a bounded decision tool for agents

About Drex-MCP

Drex MCP exposes Nace.AI Drex as a bounded closed-decision tool for MCP-compatible agents. The agent supplies a question, explicit choices, and optional evidence/context; Drex returns a selected choice and probabilities. The agent remains responsible for deciding whether and how to act.

The server is a thin stdio MCP adapter to the public Drex API. It does not provide general conversation, execute the selected action, or contain a separate decision engine.

- Python 3.10+ - A Nace.AI Drex API key - An MCP client (Hermes Agent is supported through its documented stdio MCP configuration)

The server reads DREXAPIKEY from its process environment. It makes an HTTPS request to the fixed public Drex endpoint with a 30 second request timeout and 5 second connect timeout. It does not print provider responses, credentials, or exception text.

drexdecide(question, choices, evidence="")

- question: non-empty string, up to 2,000 characters - choices: 2–12 non-empty string labels, each up to 200 characters - evidence: optional string, up to 6,000 characters

The input becomes Drex's supported state and questions.decision choice schema. No unsupported API metadata is sent.

Errors use {"ok": false, "error": {"code": "...", "message": "..."}}; an upstream HTTP status is included when available. API response bodies and secrets are not included.

Hermes reads MCP servers from ~/.hermes/config.yaml. Install this package in the environment available to Hermes and merge examples/hermes/config.yaml into that file. Set DREXAPIKEY in the MCP server env mapping, then restart Hermes. See the Herm

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/colt2822--Drex-MCP.html)

Related MCP servers