Wraps the m-dev-tools catalog with three focused operations: route_intent translates plain English queries like "parse JSON in M" into typed IDs, describe fetches manifest URLs and verification commands for a given ID, and verify lists declared verification commands for a repository without running them. The server hits the live catalog at github.com/m-dev-tools/.github on every call rather than caching. Useful if you're building agents that need to discover and interact with M language tooling through natural language, or if you want programmatic access to the m-dev-tools registry metadata. Ships via PyPI and supports stdio transport.
MCP server for the m-dev-tools org catalog. Exposes three first-class agent tools:
route_intent(query) — plain-English intent → typed IDs (e.g. "parse JSON in M" → module:m-stdlib#STDJSON)describe(typed_id) — typed ID → pointer-blob (manifest URL, AGENTS.md URL, verification commands, …)verify(repo) — list a repo's declared verification commands (does not execute them)The server reads the catalog at https://github.com/m-dev-tools/.github over the network at call time; it is a thin wrapper, not a cache. See AGENTS.md for the contract and the AI users guide for the full walk-through.
mcp-name: io.github.m-dev-tools/m-dev-tools-mcp
pip install m-dev-tools-mcp
# or:
uvx m-dev-tools-mcp
# or from a GitHub Release wheel:
pip install https://github.com/m-dev-tools/m-dev-tools-mcp/releases/download/v0.2.4/m_dev_tools_mcp-0.2.4-py3-none-any.whl
Point any MCP client at the m-dev-tools-mcp binary the install provides:
{
"mcpServers": {
"m-dev-tools": { "command": "m-dev-tools-mcp" }
}
}
Or for clients that consult the public MCP registry:
io.github.m-dev-tools/m-dev-tools-mcp
make install # creates .venv and installs editable + dev deps
make test # pytest
make check # lint + mypy + test + check-manifest + check-agents
make build # → wheel-out/m_dev_tools_mcp-<ver>-py3-none-any.whl
docs/ai-discoverability/AI-discoverability-architecture.mddocs/ai-discoverability/phases/vX.Y.Z on main → .github/workflows/release.yml builds the wheel, attaches it to a GitHub Release, publishes to PyPI via Trusted Publisher OIDC, and updates the MCP registry record via GitHub OIDC.AGPL-3.0. Same license as every other m-dev-tools repo.