docvet
This server exposes docvet's docstring-quality checks to clients such as AI agents, letting you analyze Python files/directories and look up rule-level fix guidance.
Run docvet checks on a Python file or directory (directory checks are scoped to that tree, not the whole project).
Choose which checks to run:
presence,enrichment,freshness,coverage,griffe— defaulting to all exceptfreshness(needs git context);griffeis skipped if not installed.Get back JSON with
findings,summarystatistics, and optionallypresence_coveragedata.Receive structured
errorresponses for invalid paths, unknown check names, or malformed configuration instead of server crashes.List the full rule catalog (
docvet_rules) with each rule's name, check module, description, category (required/recommended), prescriptive guidance, and a fix example.
Analyzes git diff and blame history to detect stale or outdated docstrings, helping maintain documentation accuracy as code changes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@docvet Check my Python files for docstring issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
docvet
Better docstrings, better AI.
Why docvet?
docvet combines docstring presence metrics, structural checks, history-based staleness signals, and renderer diagnostics in one CLI, with editor and agent interfaces. These checks help reviewers find documentation gaps; they do not prove that prose describes runtime behavior correctly.
Layer | Check | ruff | interrogate | pydoclint | docvet |
1. Presence | "Does a docstring exist?" | Yes (D rules, opt-in) | Yes, with coverage metrics | Skips absent docstrings | Yes, with coverage metrics |
2. Style | "Is it formatted consistently?" | Yes (D rules, opt-in) | -- | Some parsing/style checks | Limited format checks |
3. Completeness | "Do sections and code structure agree?" | Partial (D rules; DOC rules in preview) | -- | Arguments, returns, yields, raises, attributes, type hints | AST-based section and agreement checks |
4. Accuracy | "What needs review for staleness?" | Structural checks above | -- | Structural checks above | Git diff/blame heuristics; no semantic proof |
5. Rendering | "Are there parser warnings?" | -- | -- | -- | Griffe diagnostics |
6. Visibility | "Is package discovery incomplete?" | -- | -- | -- | Missing |
Comparison reviewed 2026-10-21 against primary documentation: Ruff's D103 presence rule and DOC501 exception completeness rule (requires --preview and rule selection), pydoclint's supported checks and styles, and interrogate's coverage documentation. Capabilities depend on enabled rules and configuration; -- means no corresponding check is described in these sources.
pydoclint checks arguments, returns, yields, raises, class attributes, and type hints across Google, NumPy, and Sphinx styles. docvet's enrichment alone has 21 rules, including Raises, Yields, Receives, Warns, Attributes, Examples, cross-references, parameter agreement, and more. Add presence (coverage metrics + threshold enforcement), freshness (git diff/blame staleness signals), griffe rendering compatibility, and mkdocs coverage: 32 rules across 5 checks. Rule totals measure catalog entries, not equivalent coverage between tools.
Structural agreement checks compare documented elements with code structure. Freshness uses change history to suggest review: code can change without invalidating prose, and simultaneous code/docstring edits can still leave incorrect prose. Neither establishes semantic correctness.
Quickstart | GitHub Action | Pre-commit | Configuration | AI Agent Integration | Docs
Related MCP server: MCP SDD Server
What It Checks
Presence (existence) -- 2 rules:
missing-docstring overload-has-docstring
Enrichment (completeness) -- 21 rules:
missing-raises missing-returns missing-yields missing-receives missing-warns missing-deprecation missing-param-in-docstring extra-param-in-docstring missing-other-parameters missing-attributes undocumented-init-params missing-typed-attributes missing-examples missing-cross-references extra-raises-in-docstring extra-yields-in-docstring extra-returns-in-docstring missing-return-type trivial-docstring prefer-fenced-code-blocks scaffold-incomplete
Freshness (staleness signals) -- 5 rules:
stale-signature stale-body stale-import stale-drift stale-age
Griffe (rendering) -- 3 rules:
griffe-unknown-param griffe-missing-type griffe-format-warning
Coverage (visibility) -- 1 rule:
missing-init
Quickstart
pip install docvet && docvet check --allFor optional griffe rendering checks:
pip install docvet[griffe]Example output:
src/mypackage/helpers.py:1: missing-docstring Module has no docstring [required]
src/mypackage/utils.py:42: missing-raises Function 'parse_config' raises ValueError but has no Raises section [required]
src/mypackage/models.py:15: stale-signature Function 'process' signature changed but docstring not updated [required]
src/mypackage/api.py:1: missing-init Package directory missing __init__.py (invisible to mkdocs) [required]Configuration
Configure via [tool.docvet] in your pyproject.toml. All checks run and print findings. Checks listed in fail-on cause a non-zero exit code; unlisted checks are treated as warnings.
A check in fail-on that cannot run — most often griffe without the docvet[griffe] extra — never certified the gate you configured, so docvet reports it on stderr and exits 1. With --format json the run object reports status: "unavailable" and an unavailable_checks array, which is what distinguishes it from a gate that found problems. Set fail-on-unavailable = false (or pass --no-fail-on-unavailable) to warn and exit 0 instead. Unavailable checks that nothing gates on stay a quiet skip — though fail-on membership is not the only thing that gates: a min-coverage floor gates presence without naming it there.
[tool.docvet]
exclude = ["tests", "scripts"]
fail-on = ["griffe", "coverage"]
[tool.docvet.freshness]
drift-threshold = 30
age-threshold = 90Pre-commit
Add to your .pre-commit-config.yaml:
repos:
- repo: https://github.com/Alberto-Codes/docvet
rev: v3.0.0
hooks:
- id: docvetFor griffe rendering checks, add the optional dependency:
repos:
- repo: https://github.com/Alberto-Codes/docvet
rev: v3.0.0
hooks:
- id: docvet
additional_dependencies: [griffe]GitHub Action
Add docvet to your GitHub Actions workflow — findings appear as inline annotations on your PR:
- uses: Alberto-Codes/docvet@v3.0.0Select specific checks or pin a version:
- uses: Alberto-Codes/docvet@v3.0.0
with:
checks: 'enrichment,freshness'
docvet-version: '3.0.0'
python-version: '3.13'The griffe rendering check needs no setup: the action installs docvet[griffe], pinned or not, so every check the checks input offers is available. Note that docvet releases before 1.7.0 declare that extra without an upper bound, so pinning one installs whatever griffe publishes at the time rather than a version docvet was released against.
Behavior change — this can turn a passing build red.
Earlier releases installed plain
docvet, so the griffe check was skipped and contributed zero findings. It now runs.determine_run_outcome(src/docvet/reporting.py) returns exit code 1 as soon as any check listed infail-onreports findings, so if yourpyproject.tomlhasgriffein[tool.docvet] fail-on, your build goes from green to failing with no change on your side. This repository's ownci.ymldocvet job is exactly such a consumer.These are not new problems — it is the check finally running on docstrings that were always broken. To get back to green, fix the griffe findings or remove
griffefromfail-on.
AI Agent Integration
For tool-specific integration snippets, see the full AI Agent Integration guide.
Add docvet to your AI coding workflow. Drop this into your CLAUDE.md, .cursorrules, or agent configuration:
## Docstring Quality
After modifying Python functions, classes, or modules, run `docvet check` and fix all findings before committing.Recommended pyproject.toml configuration:
[tool.docvet]
fail-on = ["enrichment", "freshness", "coverage", "griffe"]Subcommand Quick Reference
Command | Description |
| Run all enabled checks (default: git diff files) |
| Run all checks on entire codebase |
| Run all checks on staged files only |
| Check for missing docstrings with coverage metrics |
| Check for missing docstring sections |
| Flag potentially stale docstrings via git |
| Review potential staleness via git blame |
| Find files invisible to mkdocs |
| Check mkdocs rendering compatibility |
| Scaffold missing docstring sections |
| Preview scaffolding changes without writing files |
| Show effective configuration with source annotations |
| Start LSP server for real-time editor diagnostics |
| Start MCP server for AI agent integration |
Better Docstrings, Better AI
AI coding agents rely on docstrings as context when generating and modifying code. Agents modify code but often leave docstrings stale, and research shows stale or incorrect documentation is actively harmful, worse than no docs at all:
Incorrect docs degrade LLM task success by 22.6 percentage points
Comment density improves code generation by 40-54%
Misleading comments reduce LLM fault localization accuracy to 24.55%
Performance drops substantially without docstrings
As the 2025 DORA report puts it: "AI doesn't fix a team; it amplifies what's already there." The only signal correlating with AI productivity is code quality.
docvet's freshness heuristics flag potential staleness for review, and its enrichment rules check supported docstring sections against code structure. Run docvet check in your CI, pre-commit hooks, or agent toolchain.
Badge
Add a badge to your project to show your docs are vetted:
[](https://github.com/Alberto-Codes/docvet)Used By
Are you using docvet? Open a pull request to add your project here.
License
MIT -- see LICENSE for details.
mcp-name: io.github.Alberto-Codes/docvet
Available Tools
2 toolsdocvet_checkA
Run docvet checks on Python files.
Analyzes Python source files for docstring quality issues. Runs all
enabled checks except freshness by default (freshness requires git
context; griffe also excluded when not installed). When *path* is a
directory, only files within that directory tree are checked (not the
entire project). Returns a JSON object with findings, summary
statistics, and optional presence coverage data. Invalid
configuration triggers a structured error response instead of
crashing the server. Input, read, decode, and parse failures report
an incomplete run with unique attempted, analyzed, and failed file counts.
Presence coverage explicitly marks incomplete results, with a null
percentage when no input could be analyzed. Legitimate empty selections
succeed without requiring optional check dependencies or git context.
Args:
path: Path to a Python file or directory to check.
checks: Optional list of check names to run. Valid names are
``presence``, ``enrichment``, ``freshness``, ``coverage``,
``griffe``. Defaults to all except freshness.
Returns:
JSON string with ``findings``, ``summary``, and optionally
``presence_coverage`` keys. Returns an ``error`` key on
invalid path, unknown check name, or malformed configuration.
Call docvet_rules() for per-rule fix guidance and format examples.
Inputs: path (required), checks. Returns: result
docvet_rulesB
List all available docvet rules with fix guidance.
Returns the complete rule catalog with rule name, associated check
module, human-readable description, category (required or
recommended), prescriptive fix guidance, and a format example.
Returns:
JSON string with a ``rules`` array containing objects with
``name``, ``check``, ``description``, ``category``,
``guidance``, and ``fix_example`` keys.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: docvet_rules is a read-only catalog lookup while docvet_check executes analysis on files. An agent can easily tell which to call for discovery versus execution.
Both tools share the docvet_ prefix, giving a predictable namespace and readable names. The slight verb/noun mismatch between docvet_rules (noun) and docvet_check (verb) is a minor deviation but still coherent.
Two tools is on the thin side for the domain; a linter commonly benefits from separate config, fix, or freshness-context tools. It works but feels under-scoped for the apparent feature set (presence, enrichment, coverage, griffe, freshness).
Discovery (rules) and execution (check) cover the core linting lifecycle, with rules providing fix guidance. However there is no auto-fix operation despite the emphasis on fix guidance, and freshness/git-context handling is bundled rather than exposed, a minor gap.
Maintenance
Related MCP Connectors
Zero-dependency anti-slop linter & Cloud MCP for AI-written docs, slides, and web UI.
711Enforces architectural invariants and code quality rules inside your AI agent's edit loop.
MCP server for agentverse documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCode linting and style checking tools for AI agents, exposed as an MCP server. Supports style checks, naming conventions, complexity analysis, dead code detection, and import analysis.40 npmMIT
- AlicenseCqualityBmaintenanceAn MCP server implementing Spec-Driven Development workflows for AI-agent CLIs and IDEs like Claude Code and Cursor, enabling spec-first development with automated workflow guidance and quality checks.1783 npm54MIT
- FlicenseNot gradedqualityDmaintenanceA Python-based MCP server that enforces configurable Quality Assurance automation strategies for AI coding agents, ensuring generated tests adhere to strict architectural and testing standards.-
- AlicenseNot gradedqualityDmaintenanceMCP server that enables coding agents to check documentation claims against source code, detecting drift and suggesting fixes.11 npm2MIT