mathlas

Why this score

1 public GitHub projects have this in their committed setup (counted 2026-10-07). That counts people who kept it, not people who starred it. Private projects aren't visible, so the real number is higher.

Popularity score: 56/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Nov 4, 2026 at the PyPI package mathlas-mcp@1.5.0, with Cisco's open-source skill-scanner.

What its code does:

• Runs shell commands Common for dev tools. Read the commands it runs.mathlas/funsearch.py:243, mathlas/server.py:1 and 1 more
• Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.mathlas/ramanujan.py:197, mathlas/retrieve/rerank.py:109 and 2 more
• Makes network requestsmathlas/formal_search.py:173 and 1 more
• Uses dependencies without a pinned version A later version of a dependency could change what runs.pyproject.toml:30 and 8 more

Web addresses in its code:

• oeis.orgmathlas/sequence.py:79
• elan.lean-lang.orgmathlas/server.py:809
• leanprover-community.github.iomathlas/formal_search.py:183
• leansearch.netmathlas/formal_search.py:40
• loogle.lean-lang.orgmathlas/formal_search.py:39

These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.