Mathlas
Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.
{ "mcpServers": { "archerkattri-mathlas": { "command": "uvx", "args": [ "mathlas-mcp==1.5.0" ], "env": { "MATHLAS_SEED": "<value>", "MATHLAS_INDEX": "<value>" } } }}.cursor/mcp.jsonMCP server
- Transport
- stdio
- Status
- Local
エージェントを強化
このサーバーを追加
The publisher's own command. Not a PlugMCP endpoint.
キーとログ付きでコピーをホスト。
Local command
uvx mathlas-mcp==1.5.0Credentials from the publisher
- MATHLAS_SEED — Set to 1 to force the lightweight built-in seed corpus and never load the multi-GB prebuilt index (fast cold start).
- MATHLAS_INDEX — Path to a prebuilt index .npz to serve for search_existing_math (optional; the seed corpus is used when absent).
Claude Code has no install link for a local command. Copy the command below and run it in a terminal.
shClaude Code
MATHLAS_SEED=<value> MATHLAS_INDEX=<value> claude mcp add archerkattri-mathlas -- uvx mathlas-mcp==1.5.0Run in a terminal.
jsonClaude Desktop
{ "mcpServers": { "archerkattri-mathlas": { "command": "uvx", "args": [ "mathlas-mcp==1.5.0" ], "env": { "MATHLAS_SEED": "<value>", "MATHLAS_INDEX": "<value>" } } }}claude_desktop_config.json
Local · pypiPublisher installStep-by-step: add this in Claude
Remote URL or a command on your machine? How the two installs differ
PlugMCP で実行
キーとログ付きでコピーをホスト。
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動Server facts
Local- Transport
- stdio
- License
- Apache-2.0
- API key
- MATHLAS_SEED, MATHLAS_INDEX
- Last checked
- 2026-10-26
- Stars
- 13
- Tools
- —
- Uptime
- —
Tools
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Questions
How do I install Mathlas?
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
Does Mathlas need an API key?
The publisher lists these environment variables: MATHLAS_SEED, MATHLAS_INDEX.
What transport does Mathlas use?
Mathlas runs locally over stdio.
When was Mathlas last checked?
Last checked 2026-10-26. Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.
From the publisher
Documentation
README is not crawled yet. Open the repository
Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.