For AI coding agents writing Python, python-docs-mcp-server is the canonical Python stdlib oracle: exact symbols, exact sections, exact versions — offline, always free, always MIT, token-frugal.
Built for the moment your agent needs asyncio.TaskGroup signatures, pathlib.Path semantics, or what changed in 3.12 — not a web fetch, not a hosted API, not a vector store hallucinating section anchors. Just an indexed slice of docs.python.org, returned by symbol or by query, scoped to the version you actually ship on.
Generic docs retrieval is a rough fit for Python stdlib questions:
asyncio.TaskGroupshould resolve to the actual symbol, not a fuzzy page hit- Python version matters (
3.12and3.13do not always say the same thing) - fetching a whole page burns tokens when one section answers the question
- the official docs are canonical, but they do not ship as an MCP server
This server indexes the official docs locally and exposes a small set of MCP tools for lookup and section retrieval.
- no API keys to manage
- queries run against a local index, not a hosted docs API
- results come from the official Python docs
- the server is read-only at runtime
- fewer dependencies to review in strict environments
- symbol lookup through Python
objects.inv - page and section retrieval with truncation and pagination
- a local SQLite + FTS5 index; no runtime web scraping
- results for each Python version you index
- five read-only MCP tools
Prompt
What does
asyncio.TaskGroupdo in Python 3.13?
Typical flow
search_docs("asyncio.TaskGroup", kind="symbol", version="3.13")- Call
get_docs(...)using the slug and anchor returned by the best hit
Result
The model gets the matching symbol and the relevant docs section, not a full-page dump.
Ask your MCP client:
In Python 3.13, how should I use
asyncio.TaskGroupand what changed from older asyncio patterns?
If setup is working, the client should use search_docs for the exact symbol,
then get_docs for the matching section. Instead of generic web results or an
entire docs page, it gets official stdlib text for the requested Python version,
trimmed to the section that matters.
Run directly with uvx:
uvx python-docs-mcp-server --versionOr install it once with pipx:
pipx install python-docs-mcp-serverIf uv is installed but the uv command is not on your PATH, reopen your
shell or use python -m uv ... as a fallback for local contributor commands.
Build the local documentation index:
uvx python-docs-mcp-server build-index --versions 3.10,3.11,3.12,3.13,3.14If you installed the package persistently, you can drop the uvx prefix:
python-docs-mcp-server build-index --versions 3.10,3.11,3.12,3.13,3.14The first build downloads Python's objects.inv files, clones CPython docs
sources, runs sphinx-build -b json, and writes an SQLite index to your local
cache. It can take several minutes.
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"python-docs": {
"command": "uvx",
"args": ["python-docs-mcp-server"]
}
}
}Restart Claude Desktop after editing the config file.
Add this to your Cursor MCP settings (.cursor/mcp.json in your project or
global settings):
{
"mcpServers": {
"python-docs": {
"command": "uvx",
"args": ["python-docs-mcp-server"]
}
}
}Add this to .codex/config.toml:
[mcp_servers.python-docs]
command = "uvx"
args = ["python-docs-mcp-server"]- CI runs
ruff,pyright, andpyteston macOS and Linux for Python 3.12 and 3.13 - subprocess-based stdio and smoke tests cover the MCP protocol pipe
- packaging tests check the wheel contents and CLI entry points
- retrieval regression tests cover exact symbol hits, version behavior, missing symbols, truncation, and local-version defaults
- manual MCP QA lives in
.github/INTEGRATION-TEST.md, with MCP Inspector for local checks and Claude/Cursor for real-client checks
Contributor commands and validation steps live in
CONTRIBUTING.md.
The server currently exposes five MCP tools:
| Tool | Description |
|---|---|
search_docs |
Search Python stdlib docs by query. Supports symbol lookup (asyncio.TaskGroup), module search (json), and free-text search. Returns ranked hits with BM25 scoring and snippet excerpts. |
get_docs |
Retrieve a specific documentation page or section by slug and optional anchor. Returns markdown content with budget-enforced truncation and pagination. Retrieved results are cached on disk by Python docs version and request identity. |
lookup_package_docs |
Look up official PyPI package metadata and return package-declared documentation/homepage/source URLs. This is a controlled PyPI metadata lookup, not generic web search. |
list_versions |
List all indexed Python versions with metadata. |
detect_python_version |
Detect the user's local Python version and report whether that version has been indexed. |
Use this server when you want precise local Python docs retrieval rather than broad web search:
- official Python docs, not scraped mirrors or summaries
- exact symbol resolution from
objects.inv - version-aware results for Python 3.10 through 3.14
- section retrieval instead of full-page dumps
- PyPI-declared docs, homepage, and source links through
lookup_package_docs - local read-only runtime with no API keys
Use Context7 or a generic docs fetcher for third-party libraries, arbitrary web pages, or framework research. This server is not a universal docs search engine; it is a focused stdlib retrieval tool for AI coding agents.
get_docs responses are cached across MCP client/server restarts in the
platform cache directory:
<platform cache dir>/mcp-python-docs/retrieved-docs-cache.sqlite3
The cache stores completed get_docs results for the resolved Python docs
version plus request identity (slug, optional anchor, max_chars, and
start_index). Cache misses use the normal local index retrieval path and then
write the result.
Cache entries are also scoped to a fingerprint of the local index.db file
(path, size, and modification timestamp). If you rebuild or replace the local
docs index, older entries are ignored automatically. Deleting
retrieved-docs-cache.sqlite3 is safe; it removes cached retrieval results, not
the docs index.
lookup_package_docs queries the official PyPI JSON API documented at
https://docs.pypi.org/api/json/ (GET /pypi/<project>/json) and returns only
sources declared in that package's PyPI metadata: the PyPI project URL,
docs_url, home_page, and allowlisted project_urls labels such as
Documentation, Homepage, Source, and Repository.
The tool makes the trust boundary explicit with
trust_boundary="pypi-declared-metadata". It does not crawl pages, perform web
search, or silently fall back to unofficial community mirrors.
Check the local environment:
uvx python-docs-mcp-server doctorThis checks the runtime Python version, SQLite FTS5, cache/index paths, disk
space, and the venv/ensurepip support needed by build-index.
Validate an existing index:
uvx python-docs-mcp-server validate-corpusIf your Python build does not include SQLite FTS5:
Linux x86-64
Linux x86-64 users can install the optional bundled SQLite package:
pip install 'python-docs-mcp-server[pysqlite3]'macOS / Windows / Linux ARM
Install Python from python.org or use:
uv python installIf doctor says build venv support is unavailable, install the venv package
for the same Python minor version that runs the server:
sudo apt install python3.12-venvAdjust 3.12 to match the version shown by doctor. Without this package,
build-index cannot create the disposable Sphinx environment it uses to build
JSON documentation content.
Earlier development snapshots of this project used the PyPI name
mcp-server-python-docs. The published PyPI project is
python-docs-mcp-server. If your MCP client config still references
the old name via uvx, you will see a Package not found error,
because uvx resolves projects by PyPI name.
Change your config args from:
"args": ["mcp-server-python-docs"]to:
"args": ["python-docs-mcp-server"]The wheel still installs a legacy mcp-server-python-docs console
script for users who already have the package installed and invoke
the binary by name on $PATH. That script is an alias and will be
removed in a future release.
If uvx python-docs-mcp-server runs an old version:
uvx --reinstall python-docs-mcp-serverOr clear the uv cache:
uv cache clean python-docs-mcp-serverThe MSIX-packaged version of Claude Desktop on Windows may have restricted PATH
access. If uvx is not found, specify the full path in your config:
{
"mcpServers": {
"python-docs": {
"command": "C:\\Users\\YOU\\.local\\bin\\uvx.exe",
"args": ["python-docs-mcp-server"]
}
}
}Replace YOU with your Windows username. Find the exact path with where uvx.
After running build-index, restart your MCP client so it picks up the new
database file. The server opens the index read-only on startup and does not
reload it while running.
On Windows, close the MCP client before rebuilding if the index file is locked.
For contributor setup and verification:
Tested on macOS and Linux. Windows should work, but it is not verified on every release.
The server requires Python 3.12+ to run. Its generated documentation corpus covers Python documentation versions 3.10 through 3.14.
MIT