Ein Model Context Protocol (MCP)-Server, der eine lokale Wolfram Engine einbindet und es KI-Assistenten (Claude, ChatGPT usw.) ermöglicht, symbolische Mathematik, numerische Analysen und Datenvisualisierungen über die Wolfram Language durchzuführen.
Haftungsausschluss: Dies ist ein inoffizielles, unabhängiges, persönliches Projekt. Es ist nicht mit Wolfram Research, Inc. verbunden, wird von dieser nicht gesponsert, unterstützt oder zertifiziert. "Wolfram", "Wolfram Language", "Wolfram Engine", "Mathematica" und zugehörige Marken sind Marken von Wolfram Research.
Diese Software enthält keine Wolfram Engine / Mathematica-Binärdateien, Aktivierungsschlüssel, Lizenzdateien oder andere proprietäre Materialien. Benutzer müssen unabhängig ihre eigene Kopie der Wolfram Engine oder von Mathematica gemäß den Lizenzbedingungen von Wolfram erwerben und ordnungsgemäß lizenzieren.
Der einzige Zweck dieses Projekts besteht darin, einer lizenzierten Einzelperson zu ermöglichen, ihren eigenen, lokal installierten Wolfram-Kernel über KI-Assistenten auf ihrem eigenen Rechner im Rahmen ihrer Lizenz zu nutzen. Die Weitergabe des Zugriffs auf die Wolfram Engine an Dritte ist kein vorgesehener Anwendungsfall und kann gegen die Lizenzbedingungen von Wolfram verstoßen.
MCP-Tools: evaluate (Text) und evaluate_image (PNG, experimentell) — alle Funktionen der Wolfram Language über zwei universelle Tools
Transporte: stdio (lokal) und Streamable HTTP
Sicherheit: Ausdrucksfilterung vor dem Kernel mit Blacklist/Whitelist-Modi und 29 Fähigkeitsgruppen
Client-RBAC: Client-spezifische Anmeldedaten, rollenbasierte Tool- und Sicherheitsrichtlinienkontrolle — zur Isolierung verschiedener KI-Clients auf demselben Rechner
OAuth 2.1: Autorisierungsserver für webbasierte MCP-Clients (Claude.ai, ChatGPT)
Konfigurationsgesteuert: Eine einzige TOML-Datei steuert das gesamte Verhalten
Related MCP server: MCP Mathematics
Python 3.11+
Wolfram Engine oder Mathematica (ordnungsgemäß lizenziert)
uv Paketmanager
# 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 serveFügen Sie dies zu Ihrer .mcp.json hinzu:
{
"mcpServers": {
"mma-mcp": {
"command": "uv",
"args": ["--directory", "/path/to/mma-mcp", "run", "mma-mcp"]
}
}
}Fügen Sie dies zu Ihrer claude_desktop_config.json hinzu (Einstellungen -> Entwickler -> Konfiguration bearbeiten):
{
"mcpServers": {
"mma-mcp": {
"command": "/path/to/mma-mcp/.venv/bin/mma-mcp"
}
}
}Unter macOS/Linux finden Sie die Konfiguration unter
~/Library/Application Support/Claude/claude_desktop_config.jsonoder~/.config/Claude/claude_desktop_config.json.
uv run mma-mcp serve --transport http --host 127.0.0.1 --port 8000Alle Einstellungen befinden sich in mma_mcp.toml (oder pyproject.toml unter [tool.mma-mcp]).
uv run mma-mcp init # generates mma_mcp.toml with commentsSchlüsselbereiche:
Bereich | Beschreibung |
| Pfad zum Wolfram-Kernel, Timeout, Ausgabeformat |
| Transportmodus, Host, Port |
| Blacklist/Whitelist-Modus, Fähigkeitsgruppen |
| Welche MCP-Tools bereitgestellt werden sollen |
| Domain und DNS-Anbieter für HTTPS (Caddy) |
| Client-Identität und rollenbasierte Zugriffskontrolle |
Ausdrücke werden gefiltert, bevor sie den Wolfram-Kernel erreichen. Symbole werden per Regex extrahiert und gegen die aktive Richtlinie geprüft.
Blacklist-Modus (Standard): blockiert gefährliche Gruppen (system_exec, Datei-I/O, Netzwerk, dynamische Auswertung).
Whitelist-Modus: erlaubt nur Symbole aus explizit aktivierten Gruppen.
29 Fähigkeitsgruppen (22 sicher + 7 gefährlich) decken ca. 6000 Wolfram Language-Symbole ab. Generieren Sie diese neu von Ihrem lokalen Kernel:
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)Bei Verwendung des HTTP-Transports können Sie Client-spezifische Anmeldedaten und Rollen konfigurieren, um verschiedene KI-Clients (z. B. Claude und ChatGPT), die mit demselben Kernel verbunden sind, zu isolieren:
# Generate password hash
uv run mma-mcp hash-password
# Generate TOML snippet for a new client
uv run mma-mcp add-client alice --role adminJeder Client ist an eine Rolle gebunden, die steuert, auf welche Tools er zugreifen kann, welche Wolfram-Symbole er verwenden darf und welche Ressourcenlimits (Timeout, Ergebnisgröße) gelten. Gleichzeitige Clients werden über einen Kernel-Worker-Pool isoliert — jeder Tool-Aufruf läuft in einem exklusiven Kernel-Prozess mit einem temporären WL-Kontext.
Siehe den Abschnitt [auth] in mma_mcp.toml für Konfigurationsdetails.
# Run tests
uv run pytest tests/ -v
# Inspect MCP tools interactively
uv run mcp dev src/mma_mcp/server.pyBefehl | Beschreibung |
| Startet den MCP-Server (Standard) |
| Generiert die Standard- |
| Generiert Sicherheitsgruppen-JSONs vom lokalen Kernel |
| Generiert Caddyfile für HTTPS |
| Hasht ein Passwort für die Konfiguration |
| Generiert TOML-Snippet für einen neuen KI-Client |
Client | Lange Berechnungen | Hinweise |
Claude.ai | ✔ Unterstützt | Sendet |
ChatGPT | ✘ Kann Zeitüberschreitung verursachen | Sendet kein |
Claude Desktop / Claude Code | Nicht getestet | Lokaler stdio-Transport |
MIT — gilt nur für den Code in diesem Repository. Die Nutzung der Wolfram Engine / Mathematica unterliegt den eigenen Lizenzbedingungen von 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…