pyro-mcp/examples/mcp_client_config.md
Thales Maciel 899a6760c4 Add host bootstrap and repair helpers
Add a dedicated pyro host surface for supported chat hosts so Claude Code, Codex, and OpenCode users can connect or repair the canonical MCP setup without hand-writing raw commands or config edits.

Implement the shared host helper layer and wire it through the CLI with connect, print-config, doctor, and repair, all generated from the same canonical pyro mcp serve command shape and project-source flags. Update the docs, public contract, examples, changelog, and roadmap so the helper flow becomes the primary onramp while raw host-specific commands remain as reference material.

Harden the verification path that this milestone exposed: temp git repos in tests now disable commit signing, socket-based port tests skip cleanly when the sandbox forbids those primitives, and make test still uses multiple cores by default but caps xdist workers to a stable value so make check stays fast and deterministic here.

Validation:
- uv lock
- UV_OFFLINE=1 UV_CACHE_DIR=.uv-cache make check
- UV_OFFLINE=1 UV_CACHE_DIR=.uv-cache make dist-check
2026-03-13 16:46:29 -03:00

1.8 KiB

MCP Client Config Example

Default for most chat hosts in 4.x: workspace-core.

Use the host-specific examples first when they apply:

Preferred repair/bootstrap helpers:

  • pyro host connect claude-code
  • pyro host connect codex
  • pyro host print-config opencode
  • pyro host doctor
  • pyro host repair opencode

Use this generic config only when the host expects a plain mcpServers JSON shape.

pyro-mcp is intended to be exposed to LLM clients through the public pyro CLI.

Generic stdio MCP configuration using uvx:

{
  "mcpServers": {
    "pyro": {
      "command": "uvx",
      "args": ["--from", "pyro-mcp", "pyro", "mcp", "serve"]
    }
  }
}

If pyro-mcp is already installed locally, the same server can be configured with:

{
  "mcpServers": {
    "pyro": {
      "command": "pyro",
      "args": ["mcp", "serve"]
    }
  }
}

If the host does not preserve the server working directory and you want the first workspace_create to start from a specific checkout, add "--project-path", "/abs/path/to/repo" after "serve" in the same args list.

Profile progression:

  • workspace-core: the default and recommended first persistent chat profile
  • vm-run: expose only vm_run
  • workspace-full: explicit advanced opt-in for shells, services, snapshots, secrets, network policy, and disk tools

Primary profile for most agents:

  • workspace-core

Use lifecycle tools only when the agent needs persistent VM state across multiple tool calls.

Other generic-client examples: