Working with AI

MCP Server

Exponential ships an MCP (Model Context Protocol) server so AI agents can manage issues with structured tool calls instead of shelling out to the CLI.

Setup

Project-local (recommended)

Create a .mcp.json at your repo root. This is checked into git, so every contributor gets the same tools:

{
  "mcpServers": {
    "xpo": {
      "command": "xpo",
      "args": ["mcp"]
    }
  }
}

User-level

Add it globally so it applies to every project:

claude mcp add xpo xpo mcp

Or manually add the snippet to ~/.claude/settings.json under mcpServers.

After any method, restart Claude Code (or run /mcp in-session).

Available tools

Tool	Description
`list`	List issues with filters (status, label, assignee, parent, text match)
`show`	Fetch one issue with description, dependencies, comments
`history`	Event audit trail for an issue
`add`	Create an issue with status, labels, parent, story points, links
`update`	Patch any subset of fields
`comment`	Add a markdown comment
`link`	Create a dependency between two issues
`start`	Start work (set to DOING + create branch)
`merge`	Merge an issue's branch and close the issue

Reduce permission prompts

Allow-list the xpo tools in .claude/settings.json:

{
  "permissions": {
    "allow": [
      "mcp__xpo__*"
    ]
  }
}

All xpo changes are git-tracked, so any mistake is recoverable with git.

Server mode

In distributed mode, the MCP endpoint is also available over HTTP at /mcp, authenticated with the same JWT as the REST API. This lets remote agents connect to a shared server.

PreviousAgent Configuration NextProject Configuration