Coding agents · MCP server
Crg: MCP server, setup and security
Crg is an open-source MCP server that lets an AI agent search code semantically and resolve call graphs for code review. Its repository has 76 stars and its last commit is from October 23, 2026 and it is licensed under Apache-2.0.
| Adoption (stars) | 19/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 15/30 |
What Crg does
According to its repository: “Token-efficient code review knowledge graph: semantic search and call-graph resolution.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Crg is listed under Coding agents, a category of 151 servers in the directory, where it ranks #92 by stars.
Topics declared by the repository: antigravity, claude-code, code-review, codex, copilot, gemini-cli.
Installing and connecting Crg
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.
The registry lists 2 secret variables to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Crg:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
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 March 20, 2026, the n24q02m/crg repository has 76 stars and 10 forks, with 1 open issues. It has more stars than 61% of the servers in the directory. It received changes this month. Version published in the registry: 3.30.0 (October 6, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Crg is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (Apache-2.0)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- Desktop Commander10.1K ★
- Ouroboros6.3K ★
- Repomix29K ★
- Claude Code Ultimate Guide6.2K ★
- Harness1.4K ★
- Appllama3K ★
Learn more
Frequently asked questions
How do I install Crg?
Crg 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 n24q02m/crg.
Is Crg free?
The code is published under the Apache-2.0 licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is Crg safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by n24q02m on GitHub. Check who maintains it before giving it access.
What are the alternatives to Crg?
In the same category: Desktop Commander, Ouroboros, Repomix, and Claude Code Ultimate Guide. Desktop Commander and Ouroboros score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
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