MCP Wolfram Alpha

1# MCP-wolfram-alpha
2
3A MCP server to connect to wolfram alpha API.
4
5<a href="https://glama.ai/mcp/servers/q5fud9cttp">
6  <img width="380" height="200" src="https://glama.ai/mcp/servers/q5fud9cttp/badge" />
7</a>
8
9## Components
10
11### Prompts
12
13This is analogous to the `!wa` bang in duckduckgo search.
14
15```python
16def wa(query: str) -> f"Use wolfram alpha to answer the following question: {query}"
17```
18
19### Tools
20
21Query Wolfram Alpha api.
22
23```python
24def query_wolfram_alpha(query: str) -> str
25```
26
27## Configuration
28
29You **must** set the `WOLFRAM_API_KEY` environment variable. Get an api ket from [Wolfram Alpha](https://products.wolframalpha.com/api).
30
31This was tested with the full results API, but it might not be required.
32
33```json
34{
35    "mcpServers": {
36        "MCP-wolfram-alpha": {
37            "command": "uv",
38            "args": [
39                "--directory",
40                "C:\\Users\\root\\Documents\\MCP-wolfram-alpha",
41                "run",
42                "MCP-wolfram-alpha"
43            ],
44            "env": {
45                "WOLFRAM_API_KEY": "your-app-id"
46            }
47        }
48    }
49}
50```
51
52## Development
53
54### Debugging
55
56Since the official MCP inspector does not have good environment support, I reccommend using wong2's [mcp-cli-inspector](https://github.com/wong2/mcp-cli).
57
58Create a config.json file in the same style as claude desktop.
59
60```json
61{
62    "mcpServers": {
63        "MCP-wolfram-alpha": {
64            "command": "uv",
65            "args": [
66                "--directory",
67                "/full/path/to/MCP-wolfram-alpha",
68                "run",
69                "MCP-wolfram-alpha"
70            ],
71            "env": {
72                "WOLFRAM_API_KEY": "your-app-id"
73            }
74        }
75    }
76}
77```
78
79Then run:
80
81```bash
82npx @wong2/mcp-cli -c .\config.json
83```
84