Which integrations are available for this server?

Provides a backend for scientific computing using Julia, supporting numeric computation and plotting. Provides a backend for scientific computing using GNU Octave, supporting numeric computation and plotting. Provides a backend for scientific computing using Python with scientific libraries (e.g., NumPy, SciPy, SymPy, pandas), supporting symbolic, numeric, and plotting capabilities. Provides a backend for scientific computing using SageMath, supporting symbolic, numeric, and plotting capabilities. Provides a backend for scientific computing using Wolfram Mathematica, supporting symbolic, numeric, plotting, and image/audio output.

How do I use scicompute-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@scicompute-mcp solve the equation x^2 + 2x - 8 = 0" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

scicompute-mcp

by sanshanjianke

Overview Schema Source Related Servers Discussions Admin

Python

Local

SciCompute MCP Server

MCP server for scientific computing with multiple backends. Provides AI coding assistants with mathematical computation and visualization capabilities.

Features

Multiple computing backends (Mathematica, Octave, Python Scientific, R, SageMath)
Image output support (plots, graphics)
Automatic backend selection
Persistent session state (variables persist across calls)
Documentation query for unknown symbols
Multi-platform support (Claude Code, Claude Desktop, OpenCode/Crush)
Recommended: Use alongside official MATLAB MCP Server for MATLAB support

Related MCP server: axiomatic-mcp

Supported Backends

Backend	Status	Capabilities
Mathematica	✅ Ready	symbolic, numeric, plot, image, audio
SageMath	✅ Ready	symbolic, numeric, plot
Python Scientific	✅ Ready	symbolic, numeric, plot
R	✅ Ready	numeric, plot
Octave	✅ Ready	numeric, plot
Julia	✅ Ready	numeric, plot
Maxima	✅ Ready	symbolic, numeric, plot

MATLAB Support

For MATLAB support, we recommend using the official MATLAB MCP Core Server from MathWorks alongside SciCompute:

Why use the official server?

No Python version restrictions (works with any Python version)
No library installation or patching required
Standalone Go binary with no dependencies
Additional features: code analysis, test running, toolbox detection

Installation:

Download the MATLAB MCP Core Server binary from the latest release:

# Linux x86_64
curl -L -o ~/matlab-mcp-core-server https://github.com/matlab/matlab-mcp-core-server/releases/latest/download/matlab-mcp-core-server-glnxa64
chmod +x ~/matlab-mcp-core-server

Configure both servers in your MCP config:

{
  "mcpServers": {
    "scicompute": {
      "command": "uvx",
      "args": ["scicompute-mcp"]
    },
    "matlab": {
      "command": "/home/username/matlab-mcp-core-server",
      "args": ["--matlab-root=/usr/local/MATLAB/R2024a"]
    }
  }
}

See the MATLAB MCP Core Server documentation for more details.

Installation

Tip: Ask your AI assistant to install it for you! Just say "Install scicompute-mcp" and it will handle everything automatically.

Quick Start (Recommended)

# Install and run with uvx (auto-manages environment)
uvx scicompute-mcp

# Or install with pip
pip install scicompute-mcp
scicompute-mcp

Debian 12+ / Ubuntu 23.04+

These systems enable PEP 668 by default, which prevents direct pip installs. Use one of these methods:

# Method 1: Use --break-system-packages (quick)
pip install --break-system-packages scicompute-mcp

# Method 2: Use pipx (recommended for CLI tools)
sudo apt install -y pipx
pipx install scicompute-mcp

# Method 3: Use China mirror (faster in China)
pip install --break-system-packages -i https://pypi.tuna.tsinghua.edu.cn/simple scicompute-mcp

After installation, add ~/.local/bin to PATH if needed:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

Install with Optional Backends

# With Mathematica support
pip install scicompute-mcp[mathematica]

# With Octave support
pip install scicompute-mcp[octave]

# With all backends
pip install scicompute-mcp[all]

Environment Architecture

┌───────────────────────────────────────────────────────────────────────────┐
│                    MCP Server (Python 3.10+)                              │
│  ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌────────────────────┐  │
│  │ Mathematica │ │   Octave    │ │   MATLAB    │ │   py_scientific    │  │
│  │   Backend   │ │   Backend   │ │   Backend   │ │  (same Python env) │  │
│  └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ └────────────────────┘  │
│         │               │               │                                  │
│         ▼               ▼               ▼                                  │
│  ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐         │
│  │  Wolfram    │ │   octave    │ │   MATLAB    │ │      R      │  sage   │
│  │  Kernel     │ │   process   │ │   process   │ │   process   │ process │
│  └─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘         │
│         │               │               │               │         │       │
│         ▼               ▼               ▼               ▼         ▼       │
│   Independent     Independent      Independent     Independent  conda     │
│   (official)      (apt/brew)       (official)      (apt/brew)  env       │
└───────────────────────────────────────────────────────────────────────────┘

Key Points:

MCP server only needs one Python environment
Each backend (except py_scientific) runs as independent process, not sharing Python environment
SageMath requires separate conda environment (Python < 3.13)

Step 1: Install Computing Backends

Install the computing backends you need (not all required):

Python Scientific Backend

Pre-installed with the main package, no additional configuration needed.

SageMath Backend

SageMath requires Python < 3.13, must be installed separately via conda:

# Configure mirror (optional, recommended for users in China)
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/

# Create SageMath environment
conda create -n sage python=3.11 -y
conda install -n sage -c conda-forge sage -y

Configure path (choose one):

# Method A: Environment variable (recommended)
export SAGE_PATH="$HOME/miniconda3/envs/sage/bin/sage"

# Method B: Modify SAGE_PATH in code
# Edit src/scicompute_mcp/backends/sage.py

R Backend

# Ubuntu/Debian
sudo apt install r-base

# macOS
brew install r

# Windows: Download from CRAN

Octave Backend

# Ubuntu/Debian
sudo apt install octave gnuplot

# macOS
brew install octave gnuplot

# Windows: Download Octave installer

Julia Backend

# Install Julia (recommended: use juliaup)
curl -fsSL https://install.julialang.org | sh

# Or download from https://julialang.org/downloads/

# Install Python package
pip install juliacall

Mathematica Backend

Purchase and install from Wolfram website
Configure path:

export MATHEMATICA_KERNEL_PATH="/usr/local/Wolfram/Wolfram/14.3/Executables/WolframKernel"

Configuration

Environment Variables

Variable	Description	Example
`SAGE_PATH`	SageMath path	`$HOME/miniconda3/envs/sage/bin/sage`
`MATHEMATICA_KERNEL_PATH`	WolframKernel path	`/usr/local/Wolfram/Wolfram/14.3/Executables/WolframKernel`
`JULIA_PATH`	Julia executable path	`$HOME/.juliaup/bin/julia`
`SCICOMPUTE_PRIORITY`	Backend priority	`mathematica,sage,julia,py_scientific`

Claude Code (`.mcp.json`)

{
  "mcpServers": {
    "scicompute": {
      "command": "uvx",
      "args": ["scicompute-mcp"]
    }
  }
}

Claude Desktop (`claude_desktop_config.json`)

{
  "mcpServers": {
    "scicompute": {
      "command": "uvx",
      "args": ["scicompute-mcp"]
    }
  }
}

OpenCode / Crush

OpenCode 1.4.6+

OpenCode 1.4.6+ reads configuration from ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "scicompute": {
      "type": "local",
      "command": ["/home/username/.local/bin/scicompute-mcp"]
    }
  }
}

Important: Use absolute path to scicompute-mcp (from pip install). Avoid uvx because it downloads dependencies on first run, which may timeout.

To verify:

opencode mcp list

Using `opencode mcp add` (Interactive)

Alternatively, add via interactive command:

opencode mcp add
# Name: scicompute
# Type: Local
# Command: /home/username/.local/bin/scicompute-mcp

Older OpenCode versions

For older versions, use ~/.opencode.json:

{
  "mcpServers": {
    "scicompute": {
      "type": "stdio",
      "command": "/home/username/.local/bin/scicompute-mcp"
    }
  }
}

Local Development

For development or if you want to use a local installation:

{
  "mcpServers": {
    "scicompute": {
      "command": "/path/to/.venv/bin/python",
      "args": ["-m", "scicompute_mcp.server"]
    }
  }
}

Multi-Platform Support

This project supports multiple AI assistant platforms. Configuration templates are provided in the configs/ directory:

File	Platform
`configs/claude-code.json`	Claude Code
`configs/claude-desktop.json`	Claude Desktop
`configs/opencode.json`	OpenCode / Crush

Custom Prompts / Skills

Each platform has its own way to provide custom instructions:

Platform	Directory	Format
Claude Code	`.claude/skills/*.md`	Markdown
OpenCode / Crush	`.opencode/commands/*.md`	Markdown

Users can create custom skill files if needed.

Tools

Calling Convention

Different MCP clients have different naming conventions for calling tools:

Client	Format	Example
Claude Code	`mcp__{server}__{tool}`	`mcp__scicompute__compute(code="1+1")`
OpenCode	`{server}_{tool}`	`scicompute_compute(code="1+1")`

The examples below use the base tool names (compute, list_backends, stop). Your AI assistant will automatically use the correct format for its client.

compute(code, backend?)

Execute scientific computing code.

# Plot with Octave
compute("x = 0:0.1:10; y = sin(x); plot(x, y)", "octave")

# Symbolic computation with SageMath
compute("integrate(sin(x), x)", "sage")
compute("diff(x^3 * exp(x), x)", "sage")

# Mathematica
compute("Plot[Sin[x], {x, 0, 2 Pi}]", "mathematica")
compute("Integrate[x^2, x]", "mathematica")

# R Statistics
compute("mean(rnorm(1000))", "r")
compute("hist(rnorm(1000))", "r")

# Python Scientific
compute("sp.integrate(sp.sin(sp.Symbol('x')), sp.Symbol('x'))", "py_scientific")

# Julia
compute("plot(rand(10))", "julia")
compute("sqrt(2.0)", "julia")

# MATLAB
compute("plot(1:10, rand(1,10))", "matlab")
compute("[V,D] = eig(magic(3))", "matlab")

list_backends()

List all available backends and their capabilities.

stop(backend?)

Stop backend process and clear all state. Useful to reset variables or free memory.

stop()          # List running backends (does NOT stop any)
stop("octave")  # Stop specific backend
stop("ALL")     # Stop all running backends

Safety design: Calling stop() without arguments will NOT stop any backends. It returns a list of running backends. This prevents accidental data loss.

doc(backend?, symbol?)

Get documentation URLs for computing backends. Use this to find where to look up function documentation.

# List all backends with documentation
doc()

# Get URLs for a specific backend
doc(backend="mathematica")
doc(backend="numpy")

# Get URL for a specific function
doc(backend="mathematica", symbol="Plot3D")
doc(backend="octave", symbol="linspace")

Supported backends: mathematica, numpy, scipy, matplotlib, sympy, pandas, python, r, julia, octave, sage, maxima, matlab

Usage Examples

Ask your AI assistant:

Plot sin(x) from 0 to 2π

Calculate ∫x²dx from 0 to 1

Solve x² - 4 = 0

Look up NDSolve documentation

Getting Documentation

When you need detailed documentation for a function:

Use the doc tool to get documentation URLs
Launch a subagent with Task tool to fetch and extract documentation
Supported backends: Mathematica, NumPy, SciPy, Matplotlib, SymPy, Pandas, R, Julia, Octave, SageMath, Maxima, MATLAB

Example:

# Get documentation URL
doc(backend="mathematica", symbol="Plot3D")

# Then fetch the documentation
Task(
  description="Fetch Plot3D docs",
  prompt="Fetch Mathematica documentation for Plot3D from the URL returned by doc tool",
  subagent_type="general"
)

Documentation

docs/sage.md - SageMath collaboration guide
docs/r.md - R collaboration guide
docs/maxima.md - Maxima collaboration guide
docs/octave.md - Octave collaboration guide
Use doc() tool for documentation URLs

Requirements

Miniconda (recommended) or Python 3.10+
For SageMath backend: conda environment with Python 3.11
For R backend: R installation
For Octave backend: GNU Octave + gnuplot
For Mathematica backend: Wolfram Mathematica
For MATLAB backend: MATLAB + MATLAB Engine for Python

License

Unlicense - Public Domain

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Aman-Amith-Shastry-scientific_computation_mcp AOAuth
ai.smithery
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
Research & Data
2622
Artificial Wit AIOAuth
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
Math MCP Learning A
io.github.clouatre-labs
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
Education & Learning Tools Research & Data Developer Tools
1725
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2

Related MCP Servers

mma-mcp
AI & Machine Learning Developer Tools Data Visualization
siqiliu-tsinghua
A
license
A
quality
F
maintenance
An MCP server that connects AI assistants to a local Wolfram Engine, enabling symbolic math, numerical analysis, and data visualization through Wolfram Language. It provides secure expression filtering, client authentication, and supports both local stdio and HTTP transports.
Updated a month ago (2026-08-04 02:15 UTC)
2
32
MIT
axiomatic-mcpofficial
Research & Data AI & Machine Learning
Axiomatic-AI
A
license
B
quality
B
maintenance
MCP server enabling AI assistants to access the Axiomatic_AI Platform for scientific computing, document processing, and photonic circuit design.
Updated 8 hours ago (2026-09-16 08:38 UTC)
50
268 PyPI
23
MIT
SageMath MCP Server
Research & Data Education & Learning Tools
XBP-Europe
A
license
B
quality
A
maintenance
A universal mathematics MCP server that gives LLM clients full access to SageMath for symbolic calculus, number theory, linear algebra, and more, with persistent state across tool calls.
Updated 9 days ago (2026-09-07 21:51 UTC)
40
121 PyPI
14
MIT
Math MCP Server
Research & Data Developer Tools
YasogaN
A
license
A
quality
C
maintenance
A Model Context Protocol server that exposes 8 mathematical tools (arithmetic, algebra, calculus, matrix operations, statistics, probability, unit conversions) to any MCP-compatible AI agent, enabling mathematical computations without code.
Updated 2 months ago (2026-08-01 02:45 UTC)
8
9 npm
1
MIT

Appeared in Searches

A server to improve math capability of AI