← All integrations

LangChain integration

LangChain BaseTool subclass wrapping the agent-trust-scan endpoint. Drop into any LangChain agent.

Reference docs: https://python.langchain.com/docs/concepts/tools/  |  Machine-readable: /integrations/langchain.json

Snippet

from langchain.tools import BaseTool
from pydantic import BaseModel, Field
import httpx


class AgentTrustScanInput(BaseModel):
    target_url: str = Field(description="Agent endpoint or card URL to scan.")


class OntarioAgentTrustScan(BaseTool):
    name: str = "ontario_agent_trust_scan"
    description: str = (
        "Scan an AI agent surface for trust signals. "
        "Paid endpoint (0.01 USDC via x402)."
    )
    args_schema: type = AgentTrustScanInput

    def _run(self, target_url: str) -> dict:
        r = httpx.post(
            "https://ontarioprotocol.com/api/x402/agent-trust-scan",
            json={"target_url": target_url},
            timeout=30,
        )
        r.raise_for_status()
        return r.json()

Endpoints wired

• POST /api/x402/agent-trust-scan — 0.01 USDC
• GET /api/x402/reputation/<agent_id> — 0.001 USDC
• POST /api/x402/list-agent — 0.10 USDC
• POST /api/x402/list-service — 0.50 USDC

Want to test without paying? Use POST /api/demo/agent-trust-scan — free, rate-limited, same response shape.