DevInsight MCP
Enables Claude to inspect, analyze, and grade local Git repositories with tools for stats, TODO scanning, git history, large file detection, health scores, and tech stack fingerprinting.
README
DevInsight MCP
A lightweight Model Context Protocol (MCP) server that gives Claude the ability to inspect, analyze, and grade local Git repositories.
Built with Anthropic's official Python MCP SDK, DevInsight demonstrates all three MCP primitives ā Tools, Resources, and Prompts ā through practical developer workflows: language stats, TODO tracking, git history, large-file detection, an overall repo health score, and technology-stack fingerprinting.
Demo

A live session driving the DevInsight tools against this very repository ā repo stats, TODO scan, and large-file detection.
⨠Features
- š Repository statistics ā languages, file counts, line counts
- š Scan projects for
TODO,FIXME,HACK, andXXX - š Summarize recent Git commits (author, date, message, +/- lines)
- š Detect oversized source files that are due for a refactor
- 𩺠Score overall repository health (README/LICENSE/tests/git, TODO density, file size) with concrete recommendations
- š§° Fingerprint a project's tech stack ā languages, frameworks, databases, package managers, CI/CD, deployment
- š³ Browse repositories through an MCP Resource
- š¤ Review and prioritize TODOs using an MCP Prompt
Scanning automatically skips noise: .git, .github, node_modules, virtualenvs, build/cache directories, lock files, and binary assets ā see Repository Scanning below.
Why DevInsight?
Developers spend a surprising amount of time manually inspecting repositories:
- searching for TODOs
- checking Git history
- counting files
- finding oversized modules
- judging whether a project is in good shape before diving in
DevInsight exposes these tasks as MCP tools so Claude can perform them for you, directly in conversation.
Instead of manually searching your project, you can simply ask:
"Summarize the last 10 commits."
"Find every TODO and tell me which ones are most important."
"Which files are becoming too large?"
"How healthy is this repo, and what should I fix first?"
"What's the tech stack of this project?"
Installation
Clone the repository
git clone https://github.com/AzamHosseinian/devinsight-mcp.git
cd devinsight-mcp
Create a virtual environment
python3 -m venv .venv
source .venv/bin/activate
Windows:
.venv\Scripts\activate
Install dependencies
pip install -r requirements.txt
Try it with the MCP Inspector
The easiest way to test the server standalone is with the official MCP Inspector:
mcp dev server.py
The Inspector lets you invoke every Tool, inspect Resources, test Prompts, and debug raw responses ā all in the browser, no client app required.
Claude Desktop Setup
Add DevInsight to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"devinsight": {
"command": "/absolute/path/to/devinsight-mcp/.venv/bin/python3",
"args": [
"/absolute/path/to/devinsight-mcp/server.py"
]
}
}
}
Using the virtual environment's Python interpreter (rather than a bare python) ensures Claude Desktop finds the mcp package regardless of what's active in your shell.
Fully quit and reopen Claude Desktop afterwards ā it only reads this file on startup. Then try:
Use
repo_statson ~/projects/my-app
or
Review all TODOs in this repository.
Available Tools
| Primitive | Name | Purpose |
|---|---|---|
| Tool | repo_stats |
Language and line-count breakdown |
| Tool | find_todos |
Find TODO / FIXME / HACK / XXX comments |
| Tool | git_log_summary |
Summarize recent Git activity |
| Tool | find_large_files |
Detect files exceeding a configurable size |
| Tool | repo_health |
Overall 0-100 health score with recommendations |
| Tool | tech_stack |
Detect languages, frameworks, databases, package managers, CI/CD, deployment |
| Resource | repo://tree/{path} |
Render the repository tree |
| Prompt | review_todos |
Ask Claude to prioritize TODOs |
Usage examples
repo_stats(path="~/projects/my-app")
ā { "total_files": 142, "total_lines": 18734,
"by_extension": { ".ts": {...}, ".tsx": {...}, ... } }
find_todos(path=".", max_results=50)
ā [ { "file": "src/api.ts", "line_number": 42,
"tag": "TODO", "text": "handle retry backoff" }, ... ]
git_log_summary(path=".", count=5)
ā { "commits": [ { "hash": "a1b2c3d4", "author": "...",
"date": "2026-07-10", "message": "...",
"insertions": 12, "deletions": 3 }, ... ] }
find_large_files(path=".", threshold_lines=300)
ā [ { "file": "src/legacy/parser.py", "lines": 812 }, ... ]
repo_health(path=".")
ā { "score": 78,
"checks": { "has_git": true, "has_readme": true,
"has_license": true, "has_tests": false },
"recommendations": [ "Add a test suite ..." ] }
tech_stack(path=".")
ā { "languages": ["Python"], "frameworks": ["FastAPI"],
"databases": ["PostgreSQL"], "package_managers": ["pip"],
"ci_cd": ["GitHub Actions"], "deployment": ["Docker"] }
Repository Scanning
Statistics tools (repo_stats, find_todos, find_large_files, repo_health) walk the repo while pruning directories as they go ā ignored subtrees are never descended into.
Ignored directories: .git, .github, node_modules, venv, .venv, env, __pycache__, dist, build, .next, .nuxt, .svelte-kit, .idea, .vscode, target, coverage, htmlcov, .pytest_cache, .mypy_cache, .cache
Excluded from statistics: lock files (package-lock.json, pnpm-lock.yaml, yarn.lock, poetry.lock, Cargo.lock, Gemfile.lock, composer.lock, uv.lock, bun.lockb) and binary assets (.png, .jpg, .jpeg, .gif, .pdf, .zip, .exe, .dll) ā these are real project content, but noise in line/size stats.
tech_stack looks at these same files directly, since a lock file's mere presence is a useful package-manager signal.
Architecture
Claude Desktop
ā
ā¼
DevInsight MCP Server
ā
āāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāā
ā¼ ā¼ ā¼
Git Repository File System Git History
Project Structure
devinsight-mcp/
āāā server.py
āāā requirements.txt
āāā pyproject.toml
āāā README.md
āāā docs/
ā āāā demo.gif
ā āāā demo.tape
ā āāā demo_cli.py
āāā .gitignore
Roadmap
- [x] Repository statistics
- [x] TODO scanner
- [x] Git history summaries
- [x] Large file detection
- [x] Repository tree resource
- [x] TODO review prompt
- [x] Overall repo health score
- [x] Tech stack detection
- [ ] Lint summary tool
- [ ] GitHub Issues integration
- [ ] Dependency vulnerability analysis
- [ ] Pull request insights
Tech Stack
- Python
- Anthropic MCP Python SDK
- Git
- Claude Desktop
- Model Context Protocol (MCP)
Contributing
Contributions, suggestions, and feedback are welcome.
If you'd like to improve DevInsight, feel free to open an issue or submit a pull request.
License
MIT ā see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.