Un servidor del Model Context Protocol (MCP) que envuelve un Wolfram Engine local, permitiendo a los asistentes de IA (Claude, ChatGPT, etc.) realizar matemáticas simbólicas, análisis numérico y visualización de datos mediante Wolfram Language.
Aviso legal: Este es un proyecto personal, independiente y no oficial. No está afiliado, patrocinado, respaldado ni certificado por Wolfram Research, Inc. "Wolfram", "Wolfram Language", "Wolfram Engine", "Mathematica" y las marcas relacionadas son marcas comerciales de Wolfram Research.
Este software no incluye binarios de Wolfram Engine / Mathematica, claves de activación, archivos de licencia u otros materiales propietarios. Los usuarios deben obtener y licenciar de forma independiente su propia copia de Wolfram Engine o Mathematica de acuerdo con los términos de licencia de Wolfram.
El único propósito de este proyecto es permitir que un individuo con licencia invoque su propio kernel de Wolfram instalado localmente a través de asistentes de IA en su propia máquina, dentro del alcance permitido por su licencia. La redistribución del acceso a Wolfram Engine a terceros no es un caso de uso previsto y puede violar los términos de licencia de Wolfram.
Herramientas MCP: evaluate (texto) y evaluate_image (PNG, experimental) — todas las capacidades de Wolfram Language a través de dos herramientas universales
Transportes: stdio (local) y HTTP con soporte para streaming
Seguridad: Filtrado de expresiones previo al kernel con modos de lista negra/lista blanca y 29 grupos de capacidades
RBAC de cliente: Credenciales por cliente, control de herramientas y políticas de seguridad por rol — para aislar diferentes clientes de IA en la misma máquina
OAuth 2.1: Servidor de autorización para clientes MCP basados en web (Claude.ai, ChatGPT)
Configuración basada en archivos: Un único archivo TOML controla todo el comportamiento
Related MCP server: MCP Mathematics
Python 3.11+
Wolfram Engine o Mathematica (con licencia adecuada)
Gestor de paquetes uv
# Clone and install
git clone https://github.com/siqiliu-tsinghua/mma-mcp.git
cd mma-mcp
uv sync
# Graphics export dependencies (headless servers only — desktops already have these)
sudo apt-get install -y libfontconfig1 libgl1 libasound2t64 libxkbcommon0 libegl1
# Generate default config
uv run mma-mcp init
# Generate security group files (requires Wolfram kernel, ~1 min)
uv run mma-mcp setup
# Start server (stdio, for local MCP clients)
uv run mma-mcp serveAñadir a su .mcp.json:
{
"mcpServers": {
"mma-mcp": {
"command": "uv",
"args": ["--directory", "/path/to/mma-mcp", "run", "mma-mcp"]
}
}
}Añadir a su claude_desktop_config.json (Configuración -> Desarrollador -> Editar configuración):
{
"mcpServers": {
"mma-mcp": {
"command": "/path/to/mma-mcp/.venv/bin/mma-mcp"
}
}
}En macOS/Linux, encuentre la configuración en
~/Library/Application Support/Claude/claude_desktop_config.jsono~/.config/Claude/claude_desktop_config.json.
uv run mma-mcp serve --transport http --host 127.0.0.1 --port 8000Todos los ajustes residen en mma_mcp.toml (o pyproject.toml bajo [tool.mma-mcp).
uv run mma-mcp init # generates mma_mcp.toml with commentsSecciones clave:
Sección | Descripción |
| Ruta del kernel de Wolfram, tiempo de espera, formato de salida |
| Modo de transporte, host, puerto |
| Modo de lista negra/lista blanca, grupos de capacidades |
| Qué herramientas MCP exponer |
| Dominio y proveedor de DNS para HTTPS (Caddy) |
| Identidad del cliente y control de acceso basado en roles |
Las expresiones se filtran antes de llegar al kernel de Wolfram. Los símbolos se extraen mediante expresiones regulares y se verifican contra la política activa.
Modo de lista negra (predeterminado): bloquea grupos peligrosos (system_exec, E/S de archivos, redes, evaluación dinámica).
Modo de lista blanca: solo permite símbolos de grupos habilitados explícitamente.
29 grupos de capacidades (22 seguros + 7 peligrosos) cubren aproximadamente 6000 símbolos de Wolfram Language. Regenere desde su kernel local:
uv run mma-mcp setup # required after cloning (generates from your local kernel)
uv run mma-mcp setup --force # force regeneration (e.g., after Wolfram Engine upgrade)Al usar el transporte HTTP, puede configurar credenciales y roles por cliente para aislar diferentes clientes de IA (por ejemplo, Claude y ChatGPT) que se conectan al mismo kernel:
# Generate password hash
uv run mma-mcp hash-password
# Generate TOML snippet for a new client
uv run mma-mcp add-client alice --role adminCada cliente está vinculado a un rol que controla a qué herramientas puede acceder, qué símbolos de Wolfram puede usar y límites de recursos (tiempo de espera, tamaño del resultado). Los clientes concurrentes se aíslan mediante un grupo de trabajadores del kernel: cada llamada a la herramienta se ejecuta en un proceso de kernel exclusivo con un contexto de WL temporal.
Consulte la sección [auth] en mma_mcp.toml para obtener detalles de configuración.
# Run tests
uv run pytest tests/ -v
# Inspect MCP tools interactively
uv run mcp dev src/mma_mcp/server.pyComando | Descripción |
| Iniciar el servidor MCP (predeterminado) |
| Generar |
| Generar JSONs de grupos de seguridad desde el kernel local |
| Generar Caddyfile para HTTPS |
| Hashear una contraseña para la configuración |
| Generar fragmento TOML para un nuevo cliente de IA |
Cliente | Cálculos largos | Notas |
Claude.ai | ✔ Soportado | Envía |
ChatGPT | ✘ Puede agotar el tiempo | No envía |
Claude Desktop / Claude Code | No probado | Transporte stdio local |
MIT — se aplica solo al código en este repositorio. El uso de Wolfram Engine / Mathematica se rige por los propios términos de licencia de Wolfram Research.
Evaluate a Wolfram Language expression and return the result as text.
Args: expression: A valid Wolfram Language expression string. form: Output format — TeXForm (default), OutputForm, InputForm, StandardForm, or TraditionalForm.
| Name | Required | Description | Default |
|---|---|---|---|
| expression | Yes | ||
| form | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the core behavior (evaluates expressions, returns text results) and mentions format options, but doesn't cover important behavioral aspects like error handling, computational limits, authentication requirements, or rate limits. The description adds value beyond what would be in annotations but leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly structured and front-loaded: the first sentence states the core purpose, followed by a clean parameter section. Every sentence earns its place, with zero wasted words. The formatting with 'Args:' section enhances readability without verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (expression evaluation), no annotations, and no output schema, the description does well but has gaps. It thoroughly documents parameters and purpose, but doesn't describe return value format beyond 'text' or potential error conditions. For a computational tool with no structured safety hints, more behavioral context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description fully compensates by providing comprehensive parameter documentation. It clearly explains both parameters: 'expression' as 'a valid Wolfram Language expression string' and 'form' with its five possible values and default. This adds substantial meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verb ('evaluate') and resource ('Wolfram Language expression'), and distinguishes it from sibling tool 'evaluate_image' by specifying it returns text rather than image results. The phrase 'return the result as text' explicitly differentiates it from the image-focused sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context about when to use this tool (for evaluating Wolfram Language expressions to get text results) and implies when not to use it (when image results are needed, suggesting 'evaluate_image' as an alternative). However, it doesn't explicitly state exclusion criteria or name the alternative tool directly in the main description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Evaluate a Wolfram Language expression and return the result as a PNG image.
Useful for Plot, Graphics, or any expression with visual output.
Args: expression: A valid Wolfram Language expression string.
| Name | Required | Description | Default |
|---|---|---|---|
| expression | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool evaluates expressions and returns PNG images, it lacks critical behavioral details such as error handling, performance characteristics, rate limits, authentication requirements, or what happens with invalid expressions. This leaves significant gaps in understanding how the tool behaves in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise and well-structured. It starts with the core purpose, provides usage guidelines, then clearly documents the parameter. Every sentence earns its place with no redundant information, making it easy to scan and understand quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (evaluating Wolfram Language expressions with visual output), no annotations, no output schema, and 0% schema description coverage, the description provides adequate basics but lacks completeness. It covers the purpose and parameter semantics well, but misses important behavioral context about how the tool operates, what errors might occur, and what the PNG output contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context for the single parameter: 'expression: A valid Wolfram Language expression string.' This clarifies what type of input is expected beyond the schema's basic 'string' type. Since schema description coverage is 0% and there's only one parameter, the description adequately compensates by specifying the parameter's purpose and format requirements.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Evaluate a Wolfram Language expression and return the result as a PNG image.' It specifies both the action (evaluate) and the resource (Wolfram Language expression), and distinguishes it from the sibling tool 'evaluate' by mentioning the visual output format (PNG image).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use this tool: 'Useful for Plot, Graphics, or any expression with visual output.' This gives guidance on appropriate use cases. However, it doesn't explicitly state when NOT to use it or name alternatives (like the sibling 'evaluate' tool for non-visual results), which prevents a perfect score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0evaluateevaluate_imageScored across 2 tools
The two tools have clearly distinct purposes: evaluate returns text output in various formats, while evaluate_image returns PNG images for visual output. There is no overlap or ambiguity between them, as each targets a different output type for Wolfram Language expressions.
Both tools follow a consistent verb_noun pattern with 'evaluate' as the verb and descriptive suffixes ('_image') to differentiate them. The naming is predictable and aligned, making it easy to understand their relationship and functionality.
With only two tools, this server feels too thin for its apparent scope of evaluating Wolfram Language expressions. It covers text and image output but lacks other essential operations like querying Wolfram Alpha, handling errors, or managing sessions, which limits its utility in broader workflows.
The tool surface is severely incomplete for a Wolfram Language server. It only provides evaluation with text or image output, missing critical functionality such as data import/export, symbolic computation queries, step-by-step solutions, or integration with Wolfram Cloud services, leading to significant gaps in agent capabilities.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
MCP server for building and testing AI agents with multi-model experimentation and insights.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…