
Math Mcp
io.github.andylbrummerPublished by GitHub account andylbrummerv0.1.6Updated Oct 24, 2026
GPU-accelerated MCP server: symbolic algebra, numerical computing, FFT, optimization, linear algebra
Overview
A local MCP server that gives an assistant symbolic algebra and GPU-accelerated numerical computing tools, from equation solving to FFT and optimization.
- What you can do
- Solve, differentiate, integrate and simplify symbolic expressions with SymPy-based tools. Create arrays and multiply matrices with GPU acceleration. Solve linear systems of the form Ax = b. Compute forward and inverse fast Fourier transforms. Minimize functions and find their roots.
- When to use it
- Useful when an assistant needs to do real math rather than approximate it: symbolic derivations, linear algebra, signal analysis, optimization problems, or scientific and engineering calculations that mix symbolic and numerical steps.
- Requirements
- Runs locally over stdio as a Python package, launched with uvx scicomp-math-mcp or installed via pip. No accounts, API keys or headers are declared. GPU acceleration is opt-in through the MCP_USE_GPU environment variable; without it the server runs on CPU.
Installation
In SourceWeft
- Open Math Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
scicomp-math-mcp
mcp-name: io.github.andylbrummer/math-mcp
MCP server for symbolic algebra and GPU-accelerated numerical computing.
Overview
This server provides tools for mathematical computation combining symbolic algebra with numerical computing:
- Symbolic mathematics - Equations, simplification, differentiation, integration (via SymPy)
- GPU-accelerated numerics - Fast array operations and linear algebra
- Mathematical transforms - FFT, optimization, root finding
- Linear systems - Solving systems of equations with GPU acceleration
Installation & Usage
Available Tools
Symbolic Computation
symbolic_solve- Solve symbolic equationssymbolic_diff- Compute derivativessymbolic_integrate- Compute integralssymbolic_simplify- Simplify expressions
Numerical Computing
create_array- Create arrays with various patternsmatrix_multiply- GPU-accelerated matrix multiplicationsolve_linear_system- Solve Ax = bfft/ifft- Fast Fourier transformsoptimize_function- Function minimizationfind_roots- Find function roots
Configuration
Set the MCP_USE_GPU environment variable to enable GPU acceleration:
Examples
📖 Code Examples
Practical tutorials in EXAMPLES.md:
- Projectile motion with symbolic + numerical computation
- Chemical equilibrium analysis
- Fourier signal analysis
- Circuit analysis with linear systems
- Progressive difficulty (beginner → advanced)
📚 Full Documentation
See the API documentation for complete API reference.
Part of Math-Physics-ML MCP System
Part of a comprehensive system for scientific computing. See the documentation for the complete ecosystem.
Source: servers/math-mcp/README.md at commit 798e264
Tools
0Version history
1- v0.1.6LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts