FRENES

Version control · MCP server

Culprit: MCP server, setup and security

Culprit is an open-source MCP server published on GitHub that lets an AI agent identify commits responsible for regressions and verify fixes are complete. Its repository has 6 stars and its last commit is from August 26, 2026 and it is licensed under MIT.

Actively maintained

What Culprit does

According to its repository: “Offline root-cause analysis for coding agents: rank the commit that introduced a regression, map a feature's blast radius and verify a fix is complete.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Culprit is listed under Version control, a category of 17 servers in the directory, where it ranks #16 by stars.

Topics declared by the repository: cli, code-review, developer-tools, git, pull, python.

Installing and connecting Culprit

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python. Listed systems: macOS, Windows, Linux.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Culprit. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on June 20, 2026, the noordeen123/culprit repository has 6 stars and 1 forks, with 0 open issues. It has more stars than 17% of the servers in the directory. Last change 2 months ago. Version published in the registry: 0.4.0 (July 26, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

GitHubGitHub : 33.9K33.9KMCP server azure devopsMCP server azure devops : 397397MCP git ingestMCP git ingest : 314314Atlassian dc MCPAtlassian dc MCP : 105105Gitlab mr MCPGitlab mr MCP : 9494Forgejo MCPForgejo MCP : 7070GitLab MCP Server (jmrplens)GitLab MCP Server (jmrplens) : 4545Github enterprise MCPGithub enterprise MCP : 2929CulpritCulprit : 66
GitHub stars of the most followed servers in the category (log scale); Culprit in orange. Checked October 25, 2026.

Verdict

Culprit is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Limitations

  • Few visible users

Frequently asked questions

How do I install Culprit?

Culprit is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of noordeen123/culprit.

Is Culprit free?

The code is published under the MIT licence and can be used free of charge.

Is Culprit safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by noordeen123 on GitHub. Check who maintains it before giving it access.

What are the alternatives to Culprit?

In the same category: GitHub, GitWarren, MCP server azure devops, and GitLab MCP Server (jmrplens). GitHub and GitWarren score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score