Run your first xMesh mission

One package installs both commands: xmesh runs the local runtime and xmesh-mcp lets a coding agent call it.

npm install -g @sym-bot/xmesh

Start xMesh in a terminal and leave it running. Choose the CLI where you are already signed in as the worker mind used inside missions.

XMESH_LLM_PROVIDER=cli:codex xmesh
# Or use Claude Code:
XMESH_LLM_PROVIDER=cli:claude xmesh

The API listens on http://localhost:8787. A fresh runtime with a working provider commonly reports ready:true, grounded:false: it can run work but has no mesh peers yet. That is an isolated deployment, not a broken one.

For Codex, register the bundled bridge:

codex mcp add xmesh --env XMESH_URL=http://localhost:8787 -- xmesh-mcp

For Claude Code, add this server to .mcp.json:

{
  "mcpServers": {
    "xmesh": {
      "command": "xmesh-mcp",
      "env": { "XMESH_URL": "http://localhost:8787" }
    }
  }
}

Fully restart the coding agent after adding or changing the server. MCP tool schemas are cached when the connection opens; restarting xMesh alone does not refresh them.

In the restarted coding agent, ask it to run any useful task in xMesh. You do not need to name an MCP tool or write tool syntax.

Run this task in xMesh: review this repository and identify the top three release risks.

The coding agent should invoke mesh_mission and return the mission id. Keep that id so you can ask the agent to check the mission or retrieve its final result later. Under the hood it can call mesh_missions with the exact id even after the temporary crew dissolves.