semanticapi-mcp
MCP server for Semantic API — discover and call any API using natural language
Documentation
Semantic API MCP Server
An MCP (Model Context Protocol) server that lets Claude, ChatGPT, and other LLM agents search and discover APIs using natural language via Semantic API. Ask for any API capability in plain English and get back endpoint details, parameters, auth info, and code snippets.
Install
pip install semanticapi-mcpOr run directly with uvx:
uvx semanticapi-mcpConfiguration
Get an API Key
Sign up at semanticapi.dev to get your API key.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
| `SEMANTIC_API_KEY` | Yes | — | Your Semantic API key |
| `SEMANTIC_API_URL` | No | `https://semanticapi.dev` | API base URL override |
Claude Desktop
Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):
{
"mcpServers": {
"semanticapi": {
"command": "uvx",
"args": ["semanticapi-mcp"],
"env": {
"SEMANTIC_API_KEY": "your-api-key-here"
}
}
}
}Or if installed with pip:
{
"mcpServers": {
"semanticapi": {
"command": "semanticapi-mcp",
"env": {
"SEMANTIC_API_KEY": "your-api-key-here"
}
}
}
}Tools
`semantic_query`
Search for an API capability using natural language.
Inputs:
- `query` (string, required) — What you want to do, e.g. "send an email with Gmail"
- `auto_discover` (boolean, optional, default: true) — Auto-discover new APIs if needed
Example: "Find me an API to convert currencies in real-time"
`semantic_discover`
Deep discovery of a specific provider/API by name and intent.
Inputs:
- `provider_name` (string, required) — API provider name, e.g. "stripe", "twilio"
- `user_intent` (string, optional) — What you want to do with this API
Example: Discover Stripe's capabilities for "process a refund"
`semantic_discover_url`
Analyze any API from its documentation URL.
Inputs:
- `url` (string, required) — URL of the API documentation
- `user_intent` (string, optional) — What you want to do with this API
Example: Analyze `https://docs.example.com/api` to generate a provider config
Related
- **Semantic API** — The hosted API service
- **semanticapi-engine** — Open source engine (AGPL-3.0)
- **semantic-api-skill** — Agent framework skill package
- **CLI Tool** — Command-line interface (`pip install semanticapi-cli`)
License
MIT
Frequently asked questions
What is semanticapi-mcp?
semanticapi-mcp is MCP server for Semantic API — discover and call any API using natural language
How do I install semanticapi-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is semanticapi-mcp open source?
Yes — it is hosted on GitHub at https://github.com/peter-j-thompson/semanticapi-mcp and has 1 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP