Use with AI · SQL · API

One key. Three ways to use it.

Plug Renavon into Claude Desktop, Cursor, ChatGPT, or any HTTP client. Same datasets, same warehouse, sub-second queries.

Connection details updated — MotherDuck retired 2026-05-04

Your API key is unchanged. If you previously connected via mcp-server-clickhouse with a MotherDuck token, you now use the REST API below (or any HTTP client). See the three ways to access Hong Kong data guide for the migration path. (Unrelated to this: the MCP tab below is a new, separate Renavon-hosted connector for Claude/ChatGPT/Gemini — not part of this migration.)

Step 1

Your API key

Authenticate with an API key. Free account, no credit card.

Query Endpoint POST https://renavon.com/api/v1/query

Get your API key

Step 2

Plug it in

Your personal remote MCP server URL — paste it into any MCP-compatible client. No install, no config file.

Remote MCP server URL

https://renavon-mcp-mono.onrender.com/YOUR_API_KEY/mcp

This URL contains your API key — treat it like a password. Anyone who has it can query your subscribed data.

Claude

Settings → Connectors → Add custom connector. Paste the URL, name it “Renavon”, leave the OAuth fields blank.

ChatGPT

Settings → Connectors (Developer Mode) → Add custom connector. Paste the URL — no separate auth header needed, the URL is your credential.

Gemini Enterprise

Data Stores → Add custom MCP data store → Streamable HTTP. Paste the URL.

Once connected, ask things like "What were last weekend's Sha Tin winners?" — the agent calls list_datasets and query and writes the SQL itself.

Cursor reads MCP servers from .cursor/mcp.json in your project. Add this and reload the window.

{
  "mcpServers": {
    "renavon": {
      "url": "https://renavon-mcp-mono.onrender.com/YOUR_API_KEY/mcp"
    }
  }
}

Cursor's chat then has direct access to the same datasets. Works in agent mode too.

Autonomous agents without native MCP support (Manus, Devin, custom scripts) can query Renavon over plain HTTP. Give the agent these four facts:

EndpointPOST https://renavon.com/api/v1/query
HeaderX-API-KEY: YOUR_API_KEY
Body{"query": "SELECT ..."}
Databaserenavon_exports (e.g. hkjc_races, crhk_companies)

Try prompts like "Using my Renavon data, show the top 10 jockeys by win rate this season" or "Chart the odds movement for the favourite in the most recent race".

import requests

API_KEY = "YOUR_API_KEY"
API_BASE = "https://renavon.com"

response = requests.post(
    f"{API_BASE}/api/v1/query",
    headers={"X-API-KEY": API_KEY, "Content-Type": "application/json"},
    json={"query": "SELECT * FROM hkjc_races LIMIT 10"}
)
data = response.json()
# data["columns"], data["data"], data["row_count"], data["truncated"]
for row in data["data"]:
    print(row)

Use pandas.DataFrame(data["data"], columns=[c["name"] for c in data["columns"]]) for a DataFrame.

Heads-up — the response is capped. Each call returns at most 10,000 rows. Check data["truncated"] on every response. For larger pulls, paginate with a keyset on your sort key. For the entire dataset as a flat file, use the CSV download instead.

curl -X POST https://renavon.com/api/v1/query \
  -H "X-API-KEY: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "SELECT * FROM hkjc_races LIMIT 10"}'

Works from any HTTP client — Postman, Insomnia, Bun, fetch in Node 18+, etc.

Step 3

Your tables

Query tables in the renavon_exports database. Example tables:

hkjc_races

SELECT * FROM hkjc_races LIMIT 10

hkjc_horses

SELECT * FROM hkjc_horses LIMIT 10

crhk_companies

SELECT * FROM crhk_companies LIMIT 10

Create a free account to see your tables.