Lets agents query the Wolfram Alpha API for computational and factual answers.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add wolfram-alpha-secretiveshell --env WOLFRAM_API_KEY='<WOLFRAM_API_KEY>' -- uv --directory path/to/your/MCP-wolfram-alpha run MCP-wolfram-alpha~/.codex/config.toml
[mcp_servers.wolfram-alpha-secretiveshell]
command = "uv"
args = ["--directory", "path/to/your/MCP-wolfram-alpha", "run", "MCP-wolfram-alpha"]
env = { WOLFRAM_API_KEY = "<WOLFRAM_API_KEY>" }
# codex mcp add wolfram-alpha-secretiveshell --env WOLFRAM_API_KEY='<WOLFRAM_API_KEY>' -- uv --directory path/to/your/MCP-wolfram-alpha run MCP-wolfram-alpha~/.cursor/mcp.json
{
"mcpServers": {
"wolfram-alpha-secretiveshell": {
"command": "uv",
"args": [
"--directory",
"path/to/your/MCP-wolfram-alpha",
"run",
"MCP-wolfram-alpha"
],
"env": {
"WOLFRAM_API_KEY": "<WOLFRAM_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"wolfram-alpha-secretiveshell": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"path/to/your/MCP-wolfram-alpha",
"run",
"MCP-wolfram-alpha"
],
"env": {
"WOLFRAM_API_KEY": "<WOLFRAM_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"wolfram-alpha-secretiveshell": {
"command": "uv",
"args": [
"--directory",
"path/to/your/MCP-wolfram-alpha",
"run",
"MCP-wolfram-alpha"
],
"env": {
"WOLFRAM_API_KEY": "<WOLFRAM_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"wolfram-alpha-secretiveshell": {
"command": "uv",
"args": [
"--directory",
"path/to/your/MCP-wolfram-alpha",
"run",
"MCP-wolfram-alpha"
],
"env": {
"WOLFRAM_API_KEY": "<WOLFRAM_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"wolfram-alpha-secretiveshell": {
"command": "uv",
"args": [
"--directory",
"path/to/your/MCP-wolfram-alpha",
"run",
"MCP-wolfram-alpha"
],
"env": {
"WOLFRAM_API_KEY": "<WOLFRAM_API_KEY>"
}
}
}
}需要的环境变量
WOLFRAM_API_KEY
把占位值换成你自己的密钥；不要把密钥提交到代码仓库。