Symbolic Math MCP

by brosnanyuen

Not rated
GitHub

About

MCP server for symbolic math derivation, calculation, and verification

Details

Author
brosnanyuen
Categories
Design, Other

Setup

Install Symbolic Math MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/brosnanyuen/symbolic_math_mcp

Follow the installation instructions in the repository README, then restart your MCP client.

Symbolically verify any equation and calculation

- Python 3.11+
- fastmcp>=3.4.2
- symbolic-math-verify>=0.1.4

python3 -m venv .venv .venv/bin/python -m pip install --upgrade pip .venv/bin/python -m pip install -e .
{ "mcp_server_name": "My Symbolic Math MCP Server", "mcp_server_url": "http://localhost:8753", "max_requests": 10, "total_timeout": 600 }

- stdio://...runs the server over stdio.
- http://...runs the server over FastMCP's streamable HTTP transport.
- https://...is accepted by the config parser and uses the HTTP transport settings. In practice, TLS is typically terminated by a reverse proxy in front of the process.

.venv/bin/python run_server.py --config config.json

- input: absolute path to a.yamlsymbolic math file
- behavior: blocks untilverify_yaml_file(filename)completes or times out

{ "status": "Tool call completed!", "filename": "proof.yaml", "result": "Math proofs are valid" }
{ "status": "Tool call has timed out!", "filename": "proof.yaml", "result": "TIMEOUT ERROR!" }
{ "status": "Tool call cannot find the file based on the filename!", "filename": "proof.yaml", "result": "FILE NOT FOUND!" }
{ "status": "Tool call cannot read the file!", "filename": "proof.yaml", "result": "FILE CANNOT BE READ!" }
{ "status": "Tool call has unknown error!", "filename": "proof.yaml", "result": "UNKNOWN ERROR!" }

- input: absolute directory path containing one or more.yamlsymbolic math files
- behavior: starts verification for each.yamlfile in parallel, bounded bymax_requests, and blocks until all checks finish or the total timeout is exceeded
- result keys: absolute file paths for each.yamlfile found indir_path
- failure behavior: ifdir_pathis missing, not absolute, unreadable, or contains no.yamlfiles, the tool returns the same structured error shape used bycheck_symbolic_math

{ "status": "Parallel Tool call completed!", "dir_path": "/abs/path/to/proofs", "result": { "/abs/path/to/proofs/one.yaml": "Math proofs are valid", "/abs/path/to/proofs/two.yaml": "Error! Math proofs are invalid" } }
{ "status": "Tool call has timed out!", "filename": "/abs/path/to/proofs", "result": "TIMEOUT ERROR!" }
{ "status": "Tool call cannot find the file based on the filename!", "filename": "/abs/path/to/proofs", "result": "FILE NOT FOUND!" }

The test suite is intentionally sequential.

PYTHONPATH=src /home/brosnan/symbolic_math_mcp/.venv/bin/python tests/run_tests_sequentially.py

The integration test starts a real stdio MCP server subprocess and validates:

- 5 valid YAML files intests_yaml
- 5 invalid YAML files in
tests_yaml

[mcp_servers.symbolic_math_mcp] url = "http://localhost:8753/mcp" [mcp_servers.symbolic_math_mcp.tools.check_symbolic_math] approval_mode = "approve" [mcp_servers.symbolic_math_mcp.tools.check_symbolic_math_parallel] approval_mode = "approve"

Search 3,500+ US universities, estimate admission chances, check financial aid by income bracket, and build balanced college lists. Free MCP server, no API key required. Data from IPEDS and College Scorecard

Provides astronomical data such as celestial object positions, rise/set times, and visibility information.

A collection of 19 professional tools for chemical molecular processing based on the Model Context Protocol (MCP).

The Ultimate Math Engine - Unifying SymPy, NumPy & Matplotlib in one powerful server! Perfect for devs & researchers.

Provides seamless access to particle physics data from the Particle Data Group (PDG) for AI assistants and applications.

Calculate permeability of porous media using the seepage distance method, derived from the Darcy's law-based formula

UK property data: crime stats, schools, demographics, valuations, comparables, Ofsted ratings

A high-performance Model Context Protocol (MCP) server for math-ing whilst vibing with LLMs. Built with Polars, Pandas, NumPy, SciPy, and SymPy for optimal calculation speed and comprehensive mathematical capabilities from basic arithmetic to advanced calculus and linear algebra.

Access Wolfram Alpha's computational knowledge engine for expert-level answers and data analysis.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.