Plug Orrery into your agent

Open Settings → Developer, click Edit Config, and add:

{
  "mcpServers": {
    "orrery": {
      "url": "https://orrery.me/api/mcp/v1"
    }
  }
}

Restart Claude Desktop. You'll see 18 Orrery tools appear in the tool picker — orrery_brief_today,orrery_market_why,orrery_search, and so on.

Edit ~/.cursor/mcp.json (create it if it doesn't exist):

{
  "mcpServers": {
    "orrery": {
      "url": "https://orrery.me/api/mcp/v1"
    }
  }
}

Reload Cursor — the agent panel surfaces Orrery tools alongside your local stdio servers.

The Anthropic SDK supports MCP transports natively. Pass the URL when constructing your agent and Claude will pick the tools up automatically.

from anthropic import Anthropic
from anthropic.lib.mcp import HTTPMCPClient

mcp = HTTPMCPClient(url="https://orrery.me/api/mcp/v1")
client = Anthropic()

resp = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=600,
    thinking={"type": "adaptive"},
    mcp_servers=[mcp],
    messages=[{
        "role": "user",
        "content": "Summarise today's biggest prediction-market move "
                   "and tell me what to verify before trusting it."
    }],
)
print(resp.content[0].text)

Each tool maps 1:1 onto an x402 endpoint. Names are namespaced under orrery_ so they sort cleanly in the tool picker. Pricing matches the catalog (preview mode is free).

• orrery_healthfree · inventory + upstream health
• orrery_brief_today$0.01 · daily brief
• orrery_markets_movers$0.005 · biggest 24h movers
• orrery_market_snapshot$0.005 · per-market snapshot
• orrery_market_why$0.02 · why did it move
• orrery_market_resolution_risk$0.01 · resolution risk
• orrery_event_cluster$0.03 · event-wide intelligence
• orrery_signals$0.01 · live signals
• orrery_signals_kind$0.01 · signals filtered to one kind
• orrery_search$0.005 · free-text market search
• orrery_events_top$0.005 · events discovery
• orrery_share_card$0.03 · share artefact
• orrery_wallet$0.02 · wallet score + dimensions
• orrery_category_intelligence$0.02 · category dashboard
• orrery_backtest$0.02 · signal backtest verdict
• orrery_trades_recent$0.005 · raw whale feed
• orrery_watchlist_summary$0.05 · composite watchlist
• orrery_portfolio_risk$0.05 · portfolio risk cockpit

# 1. Initialize handshake
curl -s https://orrery.me/api/mcp/v1 \
  -X POST -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize",
       "params":{"protocolVersion":"2024-11-05",
                 "capabilities":{},"clientInfo":{"name":"curl","version":"1"}}}'

# 2. List the 18 tools
curl -s https://orrery.me/api/mcp/v1 \
  -X POST -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'

# 3. Call a tool
curl -s https://orrery.me/api/mcp/v1 \
  -X POST -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":3,"method":"tools/call",
       "params":{"name":"orrery_brief_today","arguments":{}}}'

Orrery's MCP initialize handshake instructs your agent to refuse any request to use these tools as a buy/sell signal. The tools surface public Polymarket data with explicit calibration tiers; never predicted outcomes, never insider feeds, never copy-trading advice. The same refusal language is in/llms.txt and the agent plugin manifest.

Next steps

• • CLI version of the same surface: /docs/agents/cli
• • Raw HTTP without MCP: /docs/agents/curl
• • Service catalog (Agentic Market discovery): /.well-known/x402-services.json