Developer · Local MCP server

Mathlas

Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Archerkattri/mathlas
Version
1.5.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-07-02
Updated
2026-07-02
Publisher
Archerkattri (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/Archerkattri) · how
Repository
github.com/Archerkattri/mathlas
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIruntime: uvxmathlas-mcp1.5.0stdioMATHLAS_SEED, MATHLAS_INDEX

How to connect Mathlas

Mathlas runs locally from a Python package published to PyPI: mathlas-mcp version 1.5.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx mathlas-mcp. It reads these environment variables: MATHLAS_SEED and MATHLAS_INDEX; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "mathlas": {
      "command": "uvx",
      "args": [
        "mathlas-mcp"
      ],
      "env": {
        "MATHLAS_SEED": "<value>",
        "MATHLAS_INDEX": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
MassdriverManage the Massdriver infrastructure platform: projects, environments, deployments, and more.Local · stdioOCI image (Docker): docker.io/massdrivercloud/mcp-server:0.2.0
MasterytraceWraps the MasteryTrace CLI as a single generic MCP tool for skill-mastery tracking.Local · stdioPyPI: masterytrace-cli
Mastyf.AiRuntime proxy for MCP security, cost governance & audit.Local · stdionpm: @mastyf_ai/server
matetools MCP-SERVER35 utility tools for AI agents - mate.tools API. Hash, regex, SEO, random, DNS, SSL, JWT.Local · stdionpm: @mate-tools/mcp-server
matih.aiThe grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.Remote & Local · HTTP, stdioLive check: sign-in requiredmcp.matih.ai
MATLAB MCP ServerConnect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.Local · stdioMCP Bundle (.mcpb): matlab/matlab-mcp-server/releases/download/v0.13
Maven DecoderLets AI agents read the real source of any Maven dependency, decompiled from ~/.m2 or Central.Local · stdionpm: maven-decoder-mcp
MaxAEO AI Visibility MCPLocal-first MCP server for AI visibility, GEO/AEO, llms.txt, and AI crawler readiness audits.Local · stdionpm: maxaeo-ai-visibility-mcp