FRENES

Developer tools · MCP server

Repowise: MCP server, setup and security

Repowise is an open-source MCP server that lets an AI agent analyze repository dependencies, git history, and code health locally. Its repository has 7,893 stars and its last commit is from October 24, 2026 and it is licensed under AGPL-3.0.

Actively maintainedTop 10% by stars

What Repowise does

According to its repository: “Codebase intelligence: indexes a repo into a dependency graph, git history, defect-risk code health, generated docs and architectural decisions. Runs locally.”

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. Repowise is listed under Developer tools, a category of 475 servers in the directory, where it ranks #14 by stars.

Topics declared by the repository: code-intelligence, dead-code, developer-tools, documentation, git-analytics, open-source.

Installing and connecting Repowise

Distribution modes declared in the official MCP registry:

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

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.

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.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Repowise. 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 March 23, 2026, the repowise-dev/repowise repository has 7,893 stars and 946 forks, with 189 open issues. It has more stars than 98% of the servers in the directory. It received changes this month. Version published in the registry: 0.58.0 (October 20, 2026).

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

StorybookStorybook : 91.4K91.4KFront End ChecklistFront End Checklist : 74.6K74.6KTldrawTldraw : 51.1K51.1KCodebase MemoryCodebase Memory : 47.4K47.4KCCXTCCXT : 44.5K44.5KPostHog MCP ServerPostHog MCP Server : 40.4K40.4KClaude task masterClaude task master : 28.3K28.3KAgent Skills Search ServerAgent Skills Search Server : 26.6K26.6KRepowiseRepowise : 7.9K7.9K
GitHub stars of the most followed servers in the category (log scale); Repowise in orange. Checked October 25, 2026.

Verdict

Repowise is one of the most solid servers in its category: followed, maintained and well framed.

Strengths

  • Active project: recent commit
  • Widely followed: 7.9K stars
  • Listed in the official MCP registry

Frequently asked questions

How do I install Repowise?

Repowise 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 repowise-dev/repowise.

Is Repowise free?

The code is published under the AGPL-3.0 licence and can be used free of charge.

Is Repowise 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?

It is published in the MCP registry under the verified namespace dev.repowise, which shows the publisher controls that domain.

What are the alternatives to Repowise?

In the same category: Radar Kubernetes MCP Server, Jscpd, Apify MCP server, and Codebase Memory.

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