Skip to main content

Reusable utility methods for MCP servers

Project description

mcp-methods

Shared Rust-powered utilities for Model Context Protocol servers. Pip-installable Python library AND a native Rust crate AND a generic CLI binary — three distribution shapes, one set of primitives.

Fast file search (ripgrep-backed), GitHub integration with smart compaction, text utilities, and an rmcp-backed MCP server framework with YAML-manifest configuration. The common building blocks needed when writing MCP tool servers.

The Rust library is the source of truth; the Python wheel is a thin pyo3 binding over it. Rust consumers see zero pyo3 in their dep tree.

Install

Python — pip install

pip install mcp-methods
from mcp_methods import ElementCache, ripgrep, list_dir, github_discussions, read_file

The wheel ships the mcp-server CLI on PATH alongside the library — which mcp-server should resolve immediately. Single abi3 wheel per OS; works on Python 3.10 through 3.13 without reinstall.

Rust library — cargo add

[dependencies]
mcp-methods = "0.3"
use mcp_methods::cache::ElementCache;
use mcp_methods::{github, files, grep, list_dir, compact, html};
use mcp_methods::server::{McpServer, ServerOptions, Manifest}; // with default `server` feature

Zero pyo3 in the dep tree. The server feature (default-on) adds the rmcp-backed framework; disable with default-features = false for the bare primitives.

For pre-release coordination — pinning against a specific commit while the framework is iterating quickly — depend on a git rev:

mcp-methods = { git = "https://github.com/kkollsga/mcp-methods.git", rev = "<short SHA>", features = ["server"] }

The downstream kglite-mcp-server uses this pattern to stay locked to the exact framework rev its integration tests pass against.

CLI — cargo install (alternative path)

The CLI ships in the pip wheel by default. If you'd rather skip Python:

cargo install --git https://github.com/kkollsga/mcp-methods mcp-server

Not on crates.io — mcp-server is unpublished on purpose. The Rust library on crates.io is the published surface; the binary ships via the wheel and via git.

Documentation

Full docs at mcp-methods.readthedocs.io (Sphinx + Read the Docs, structured along Diátaxis lines):

  • Getting Started — 15-minute walkthrough from pip install to a running server
  • Core Concepts — manifest, operating modes, trust gates, downstream-binary pattern
  • Guides — writing a manifest, downstream binaries, trust gates, python bindings, watch + workspace modes
  • Reference — manifest schema, Python API, Rust API
  • Explanation — three-crate architecture, advisory-trust pattern, distribution shape

Rust API rustdoc: docs.rs/mcp-methods.

What's included

Primitive Purpose
list_dir Tree-formatted directory listing with depth, glob, .gitignore, annotation
ripgrep_files, ripgrep, ripgrep_lines Ripgrep-powered search (in-process, no subprocess)
read_file Safe file reading with path traversal protection
github_discussions, git_api GitHub issue/PR fetching with smart compaction, REST wrapper
ElementCache Drill-down cache for collapsed elements in GitHub discussions
html_to_text, compact_text, collapse_code_blocks Text utilities
extract_github_refs, detect_git_repo, validate_repo Git/GitHub helpers
mcp_methods.fastmcp Composable tool registrations for FastMCP servers
SkillRegistry, Skill, register_skills_as_prompts Operator-authored methodology as MCP prompts (three-layer: project → domain pack → bundled defaults). See crates/mcp-methods/dev-documentation/skills-aware-mcp.md for the design doc.

Plus the server framework in mcp_methods::server::*: McpServer, ServerOptions, Manifest, Workspace, watch_dir, load_env_walk, serve_prompts. See the Rust API reference.

License

MIT.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

mcp_methods-0.3.38-cp310-abi3-win_amd64.whl (7.0 MB view details)

Uploaded CPython 3.10+Windows x86-64

mcp_methods-0.3.38-cp310-abi3-manylinux_2_39_x86_64.whl (8.3 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.39+ x86-64

mcp_methods-0.3.38-cp310-abi3-macosx_11_0_arm64.whl (7.4 MB view details)

Uploaded CPython 3.10+macOS 11.0+ ARM64

File details

Details for the file mcp_methods-0.3.38-cp310-abi3-win_amd64.whl.

File metadata

File hashes

Hashes for mcp_methods-0.3.38-cp310-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 5bf09a81a599079fdd293882ca8194e5a6d5e10ca5ff92526e7f6f9d1ff9500f
MD5 64765539a19972bd7eb5aaee3123ad14
BLAKE2b-256 ca3192cb461aad07ff25a72b8604302dab7c02eddf6b720906befe9ea5c5c8fc

See more details on using hashes here.

File details

Details for the file mcp_methods-0.3.38-cp310-abi3-manylinux_2_39_x86_64.whl.

File metadata

File hashes

Hashes for mcp_methods-0.3.38-cp310-abi3-manylinux_2_39_x86_64.whl
Algorithm Hash digest
SHA256 8fabbefb6a29e9d7199b1c1b55be3564661d4c5af1189ae5a15908e5686da5af
MD5 9066bffe69b69746812b4d0952125e03
BLAKE2b-256 748d2c2df08d895ba6e1639d88bae7a1ed701695bd7509ec0c4334fd742561f5

See more details on using hashes here.

File details

Details for the file mcp_methods-0.3.38-cp310-abi3-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for mcp_methods-0.3.38-cp310-abi3-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 4ceeff59df94f06d0cc4582c56ceeb6e342166a916ed0977e8b609717c953c0f
MD5 6591fd0023072c1a23a2ce0f8b758533
BLAKE2b-256 1c3fec97cdc8ebd62e347411afc119ec6540b5d07020e4919d0eeeb461f0ac34

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page