MCP servers · c0mae

mathguard: MCP server for verifying mathematical claims and graded answers

An MCP server that checks mathematical claims, such as identities, derivatives, integrals and unit-based results, using SymPy and Pint.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

mathguard is a verification layer for mathematical claims, especially those produced by language models, which the publisher describes as good at setting up calculations but unreliable at carrying them out. It checks identities, derivatives, antiderivatives, definite integrals, solutions, limits, numerical values and dimensions. When a claim is wrong, the check can return a concrete counterexample. Each result carries one of five statuses: verified, likely, refuted, inconclusive or error.

It suits grading physics exercises or model evaluations, where a formula or number in an answer is compared with a reference result, with unit conversion and rounding taken into account. It can also read a complete worked solution written in Markdown or LaTeX, report on each step and point to the step where the calculation goes wrong.

A browser version can be tried without installation. For development use, the package is installed locally. The Python interface returns a verdict or a multi-part report with status, ok, message and counterexample fields. Grading uses a task file in YAML or JSON that holds the reference results and, optionally, given values, units, assumptions and a relative tolerance.

Limitations and requirements

A verified result means a computer algebra system confirmed the claim, not that it is formally proven. A likely result is strong numerical evidence but not a proof. Variables are assumed to be positive by default; this can be switched off with positive=False or --real. Equations that are neither identities nor consistent with earlier equations are reported as new equations and are not judged. Installation is needed for development use, and the grading mode depends on a task file that the user writes.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    mathguard

    Verify maths from language models: identities, derivations, calculus, solutions, units, answers.

    v0.4.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026