MCP Wolfram Alpha (Server + Client)

1# MCP Wolfram Alpha (Server + Client)
2Seamlessly integrate Wolfram Alpha into your chat applications.
3 
4This project implements an MCP (Model Context Protocol) server designed to interface with the Wolfram Alpha API. It enables chat-based applications to perform computational queries and retrieve structured knowledge, facilitating advanced conversational capabilities.
5 
6Included is an MCP-Client example utilizing Gemini via LangChain, demonstrating how to connect large language models to the MCP server for real-time interactions with Wolfram Alpha’s knowledge engine.
7 
8[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/akalaric/mcp-wolframalpha)
9---
10 
11## Features
12 
13-  **Wolfram|Alpha Integration** for math, science, and data queries.
14 
15-  **Modular Architecture** Easily extendable to support additional APIs and functionalities.
16 
17-  **Multi-Client Support** Seamlessly handle interactions from multiple clients or interfaces.
18 
19-  **MCP-Client example** using Gemini (via LangChain).
20-  **UI Support** using Gradio for a user-friendly web interface to interact with Google AI and Wolfram Alpha MCP server.
21 
22---
23 
24##  Installation
25 
26 
27### Clone the Repo
28   ```bash
29   git clone https://github.com/ricocf/mcp-wolframalpha.git
30 
31   cd mcp-wolframalpha
32   ```
33  
34 
35### Set Up Environment Variables
36 
37Create a .env file based on the example:
38 
39- WOLFRAM_API_KEY=your_wolframalpha_appid
40 
41- GeminiAPI=your_google_gemini_api_key *(Optional if using Client method below.)*
42 
43### Install Requirements
44   ```bash
45   pip install -r requirements.txt
46   ```
47 
48  Install the required dependencies with uv:
49  Ensure [`uv`](https://github.com/astral-sh/uv) is installed.
50 
51   ```bash
52   uv sync
53   ```
54 
55### Configuration
56 
57To use with the VSCode MCP Server:
581.  Create a configuration file at `.vscode/mcp.json` in your project root.
592.  Use the example provided in `configs/vscode_mcp.json` as a template.
603.  For more details, refer to the [VSCode MCP Server Guide](https://sebastian-petrus.medium.com/vscode-mcp-server-42286eed3ee7).
61 
62To use with Claude Desktop:
63```json
64{
65  "mcpServers": {
66    "WolframAlphaServer": {
67      "command": "python3",
68      "args": [
69        "/path/to/src/core/server.py"
70      ]
71    }
72  }
73}
74```
75## Client Usage Example
76 
77This project includes an LLM client that communicates with the MCP server.
78 
79#### Run with Gradio UI
80- Required: GeminiAPI
81- Provides a local web interface to interact with Google AI and Wolfram Alpha.
82- To run the client directly from the command line:
83```bash
84python main.py --ui
85```
86#### Docker
87To build and run the client inside a Docker container:
88```bash
89docker build -t wolframalphaui -f .devops/ui.Dockerfile .
90 
91docker run wolframalphaui
92```
93#### UI
94- Intuitive interface built with Gradio to interact with both Google AI (Gemini) and the Wolfram Alpha MCP server.
95- Allows users to switch between Wolfram Alpha, Google AI (Gemini), and query history.
96  
97![UI](configs/gradio_ui.png)
98 
99#### Run as CLI Tool
100- Required: GeminiAPI
101- To run the client directly from the command line:
102```bash
103python main.py
104```
105#### Docker
106To build and run the client inside a Docker container:
107```bash
108docker build -t wolframalpha -f .devops/llm.Dockerfile .
109 
110docker run -it wolframalpha
111```
112 
113## Contact
114 
115Feel free to give feedback. The e-mail address is shown if you execute this in a shell:
116 
117```sh
118printf "\x61\x6b\x61\x6c\x61\x72\x69\x63\x31\x40\x6f\x75\x74\x6c\x6f\x6f\x6b\x2e\x63\x6f\x6d\x0a"
119```
120 
121