Model Context Protocol

You Uclusion credentials also allows you to connect your AI agent to Uclusion

Configuration

If there is a ~/.cursor folder when the Uclusion install script runs it will add itself to the mcp.json there using the installed proxy script and your workspace ID:

{
  "mcpServers": {
    "Uclusion": {
      "command": "python3",
      "args": [
        "/usr/local/bin/uclusionMCPProxy.py",
        "dd56682c-9920-417b-be46-7a30d41bc905"
      ]
    }
  }
}

Tools

Your client loads tool definitions from the server; the Uclusion MCP server currently exposes these tools:

Tool	Description
`add_info`	Adds information to the object identified by its short code. The content appears in Uclusion as if the AI user created it (for example a reply, an associated note, or text on an option).
`approve_job`	Records an assessment of the business value of a job, including a certainty score and reason. The assessment appears in Uclusion as if the AI user created it.
`ask_question`	Creates a question with answer options about a job. The question appears in Uclusion as if the AI user created it.
`get_job`	Returns Markdown for a job (or the enclosing job when you pass a task short code) so the agent has full context: child tasks, grouped tasks, notes, questions, suggestions, and blockers. Links to content outside that job are not included. Also accepts the short code of a bug or a discussion comment that is not tied to a job.
`resolve`	Resolves a comment like a question or task or for a job moves it into Tasks Complete stage.

These tools allow you to write a prompt like this:

Use Uclusion to get J-all-284 and also read through the application documentation at https://some.documentation.com. Then as a product manager use Uclusion to ask any questions you have about the business value of this job which was proposed by a junior engineer. I will let you know when your questions are answered.