OroIntelDocs
OpenAPISign up now
For agents:start at/llms.txt·everything as Markdown at/llms-full.txt·or add theMCP server.

Use Oro Intel with the Claude Agent SDK

Give a Claude Agent SDK agent live UK tender and contract data by declaring Oro Intel's remote MCP server in mcp_servers — the agent gets all 13 oro_* tools automatically.

Prerequisites

  • An Oro Intel API key in ORO_API_KEY (create one, 250 free credits).
  • An Anthropic key in ANTHROPIC_API_KEY.
  • pip install claude-agent-sdk

Code

agent.py
"""Claude Agent SDK agent with live UK procurement data via the Oro Intel remote MCP server."""

import asyncio
import os

from claude_agent_sdk import ClaudeAgentOptions, query

ORO_API_KEY = os.environ["ORO_API_KEY"]  # https://app.oro-intel.com/dashboard/developers

options = ClaudeAgentOptions(
    mcp_servers={
        "oro-intel": {
            "type": "http",
            "url": "https://api.oro-intel.com/mcp/",  # trailing slash required
            "headers": {"Authorization": f"Bearer {ORO_API_KEY}"},
        }
    },
    allowed_tools=["mcp__oro-intel"],
)


async def main() -> None:
    async for message in query(
        prompt=(
            "Look up the UK company 'Serco' and give me its full supplier profile. "
            "Report how many public contracts it has won, and the credits_charged "
            "and credits_remaining from the tool responses."
        ),
        options=options,
    ):
        print(message)


asyncio.run(main())

Expected output

output (trimmed)
Serco Limited (company number 02048608) has won 132 public contracts.
Lookup: 5 credits; full profile: 12 credits (credits_remaining: 233).

The agent chains oro_lookup_company (5 credits) into oro_company_profile (12 credits); each tool response includes credits_charged/credits_remaining, and each tool's description states its cost up front.

Next steps