FRENES

Security · MCP server

Lachesis: MCP server, setup and security

Lachesis is an open-source MCP server that lets an AI agent analyze callers callees data flow and taint paths across source code. Its repository has 6 stars and its last commit is from October 16, 2026 and it is licensed under AGPL-3.0.

Actively maintained

What Lachesis does

According to its repository: “Code property graph for C, Python and TypeScript: callers/callees, data and taint flow with source-to-sink witnesses, points-to and guard/sink structure.”

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. Lachesis is listed under Security, a category of 133 servers in the directory, where it ranks #109 by stars.

Topics declared by the repository: appsec, call-graph, code-analysis, code-graph, program-analysis, python.

Installing and connecting Lachesis

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. Listed systems: macOS, Linux.

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 Lachesis. 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 August 10, 2026, the UnboundCompute/lachesis repository has 6 stars and 0 forks, with 0 open issues. It has more stars than 17% of the servers in the directory. It received changes this month. Version published in the registry: 0.5.3 (September 7, 2026).

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

World MonitorWorld Monitor : 89.4K89.4KSemgrepSemgrep : 17.2K17.2KIda pro MCPIda pro MCP : 13.1K13.1KGhidraMCP (LaurieWired)GhidraMCP (LaurieWired) : 11.5K11.5KRobin: AI Powered Dark Web ORobin: AI Powered Dark Web O : 7.7K7.7KJadx ai MCPJadx ai MCP : 2.9K2.9KPower BI Authoring MCP ServePower BI Authoring MCP Serve : 1.2K1.2KSafeDep Vet MCPSafeDep Vet MCP : 1.1K1.1KLachesisLachesis : 66
GitHub stars of the most followed servers in the category (log scale); Lachesis in orange. Checked October 25, 2026.

Verdict

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

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry

Limitations

  • Few visible users

Frequently asked questions

How do I install Lachesis?

Lachesis 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 UnboundCompute/lachesis.

Is Lachesis free?

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

Is Lachesis 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 UnboundCompute on GitHub. Check who maintains it before giving it access.

What are the alternatives to Lachesis?

In the same category: Semgrep, World Monitor, SafeDep Vet MCP, and Ida pro MCP. Semgrep and World Monitor 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