mcp-divineapi-docs
Serves the already-public developer documentation for the DivineAPI REST API, enabling search, endpoint lookup, and example responses without authentication.
README
Divine API - Documentation MCP Server
A public, read-only MCP server that answers "how do I use the DivineAPI REST API". It serves the already-public developer documentation: every endpoint, its parameters, its response fields, the global auth and error rules, and real captured example responses.
This server does NOT call the astrology APIs and needs NO credentials. It is a reference, not a data source. To actually run astrology requests, use the divineapi SDK or the data MCP servers:
- Indian / Vedic:
https://mcp.divineapi.com/indian/mcp - Western:
https://mcp.divineapi.com/western/mcp - Horoscope, Tarot and Numerology:
https://mcp.divineapi.com/horoscope/mcp
Public endpoint
https://mcp.divineapi.com/docs/mcp
No API key, no auth token, no OAuth. Just connect.
Tools (5)
| Tool | What it does |
|---|---|
search_docs(query, limit=8) |
Case-insensitive keyword search across every endpoint card; returns the top matching cards (most query tokens first). |
get_endpoint(path) |
The full reference card for one exact path, or the closest match / a "did you mean..." list. |
list_endpoints(category="") |
Every path [host] line, optionally filtered to a category (Indian, Western, Numerology, PDF, Horoscope, Lifestyle, Calculators). |
get_playbook() |
The global rules: auth, error semantics per host, birth params, horoscope selectors, field formats, house systems, and what not to do. |
get_example(path) |
A real captured example response body for the path (version-agnostic slug fallback), or a pointer to the card's returns: line. |
Data sources
docs-pack.txtis fetched live at startup fromhttps://developers.divineapi.com/docs-pack.txt(10s timeout); on failure the server falls back to the bundled snapshot shipped in this repo.examples.jsonis a map ofnormalized_path -> example response body, generated from the published Postman collection bybuild_examples.py. Regenerate it with:
python3 build_examples.py "/path/to/DivineAPI_Collection_with_examples_Final Version.json"
Run locally
python -m venv .venv && source .venv/bin/activate
pip install ".[http]"
# stdio (for Claude Desktop, Cursor, etc.)
divineapi-docs-mcp
# HTTP (streamable-http on :8000)
MCP_TRANSPORT=http uvicorn server:app --host 0.0.0.0 --port 8000
Deploy
Mirrors the DivineAPI data MCPs. The container runs uvicorn server:app on port 8000; docker-compose maps host port 8004 -> 8000.
docker compose up -d --build
Documentation: https://developers.divineapi.com
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.