Codeview Mcp
What is Codeview Mcp
Codeview-mcp is an AI-powered code review toolkit that integrates a MCP server and CLI to analyze GitHub pull requests (PRs). It utilizes local and cloud-based language models to identify code smells, generate summaries, provide inline comments, assess risks, and create test stubs.
Use cases
Use cases for codeview-mcp include analyzing large pull requests for security vulnerabilities, generating human-readable summaries for code changes, providing instant feedback through inline comments, and automating the creation of test stubs to enhance testing processes.
How to use
To use codeview-mcp, clone the repository from GitHub, set up a Python virtual environment, install the required dependencies, and run commands such as ‘ping’ to check PR status or ‘analyze’ to evaluate the code. Store your GitHub token securely using environment variables or a keyring.
Key features
Key features include quick AI reviews of PRs, local and cloud LLM integration for efficient analysis, inline comments for easy feedback, risk scoring to gauge potential issues, and automatic test stub generation.
Where to use
Codeview-mcp is suitable for software development teams, particularly in environments where GitHub is used for version control and code collaboration. It is beneficial in projects that require thorough code reviews to maintain quality and security.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Codeview Mcp
Codeview-mcp is an AI-powered code review toolkit that integrates a MCP server and CLI to analyze GitHub pull requests (PRs). It utilizes local and cloud-based language models to identify code smells, generate summaries, provide inline comments, assess risks, and create test stubs.
Use cases
Use cases for codeview-mcp include analyzing large pull requests for security vulnerabilities, generating human-readable summaries for code changes, providing instant feedback through inline comments, and automating the creation of test stubs to enhance testing processes.
How to use
To use codeview-mcp, clone the repository from GitHub, set up a Python virtual environment, install the required dependencies, and run commands such as ‘ping’ to check PR status or ‘analyze’ to evaluate the code. Store your GitHub token securely using environment variables or a keyring.
Key features
Key features include quick AI reviews of PRs, local and cloud LLM integration for efficient analysis, inline comments for easy feedback, risk scoring to gauge potential issues, and automatic test stub generation.
Where to use
Codeview-mcp is suitable for software development teams, particularly in environments where GitHub is used for version control and code collaboration. It is beneficial in projects that require thorough code reviews to maintain quality and security.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
CodeView MCP 🪄
Powered by MCP, CodeLlama-13B (local), Llama-3.1-8b-instant (cloud)
1 Why
Modern PRs are huge—security issues or performance regressions slip through.
ReviewGenie does a 30-second AI review:
- Static regex rules → critical smells
- Local LLM → quick heuristics (no cloud cost)
- Cloud LLM → human-style summary & risk score
- Inline comments you can accept or ignore with one click
2 What it does
| Tool | Purpose | Typical latency |
|---|---|---|
ping |
Sanity check: show title/author/state | 0.3 s |
ingest |
Fetch diff JSON + SQLite cache | 1–2 s |
analyze |
Summary, smells[], rule_hits[], risk_score ∈ [0–1] | 6–10 s |
inline |
Posts or previews comments | 0.5 s |
check |
CI gate (risk_score > threshold) |
0.2 s |
generate_tests |
Stub pytest files + open PR | 4–6 s |
Privacy note: only the diff snippet is sent to Groq; full code never leaves your machine.
3 Quick Start (5 min)
git clone https://github.com/mann-uofg/codeview-mcp.git
cd codeview-mcp
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
pip install -e .
# one-liner smoke
reviewgenie/codeview ping https://github.com/psf/requests/pull/6883
Store secrets once (env-var OR keyring):
from codeview_mcp.secret import set_in_keyring
set_in_keyring("GH_TOKEN", "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") #GitHub PAT
set_in_keyring("OPENAI_API_KEY", "gsk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx") # Groq/OpenAI key
set_in_keyring("OPENAI_BASE_URL", "https://api.groq.com/openai/v1")
Full tutorial: docs/QUICKSTART.md
4 Architecture
- SQLite → diff cache (24 h)
- ChromaDB → hunk embeddings
- Back-off → GitHub retries (403/5xx)
- Tracing → OpenTelemetry spans
- Detailed diagram:
docs/ARCHITECTURE.md
5 Benchmark
See bench/benchmarks.md:
10 popular OSS PRs → avg ⏱ 8.1 s analyze, 💰 $0.0008 Groq cost, 96 % comment acceptance.
6 Docs
- API schema:
docs/API_SCHEMA.json - CLI reference:
docs/USAGE.md - Config & env:
docs/CONFIGURATION.md - Contributing:
docs/CONTRIBUTING.md
7 Day-by-Day Log
| Day | Highlight |
|---|---|
| 0 | Project skeleton, MCP “hello” |
| 1 | GitHub ingest + diff cache |
| 2 | Local LLM smells + cloud risk |
| 3 | Inline locator + ChromaDB |
| 4 | CLI wrapper + risk gate |
| 5 | Stub test generator |
| 6 | Vector de-dup fix, CI passing |
| 7 | bench.py: eval & markdown report |
| 8 | Secrets via keyring, back-off, OpenTelemetry |
| 9 | Full docs suite & OpenAPI schema |
Full changelog: docs/CHANGELOG.md
8 Roadmap
- 🚦 Live GitHub Action auto-labels “High-Risk” PRs
- 🖼 Web UI with trace explorer
- 🐳 (Optional) Docker image for k8s / GHCR
- 🕵️♂️ Multi-language support (Go, Rust)
Star the repo ⭐ & drop an issue if you’d like to help!
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
