Skip to main content

LangChain (Python)

Connect a LangChain agent to Leadovaro using leadovaro-mcp-client. The langchain() adapter returns tool schemas ready to bind to any ChatModel, with a helper for executing tool calls.

Prerequisites​

  • Python 3.11+
  • A Leadovaro account at app.leadovaro.com with a configured toolkit
  • A Leadovaro token and an LLM API key (e.g. Anthropic)

Installation​

pip install "leadovaro-mcp-client[langchain]" langchain-anthropic python-dotenv

Environment Variables​

LEADOVARO_TOKEN=your-leadovaro-token
ANTHROPIC_API_KEY=your-anthropic-key
Get Your Credentials

How to generate a Leadovaro token and configure toolkit URL parameters

Connecting to Leadovaro​

Use LeadovaroMCPClient with the langchain() adapter to get tool schemas, bind them to a model, then use execute_langchain_tool_call to execute tool calls from the model's response:

import asyncio
import os
from dotenv import load_dotenv
from leadovaro_mcp_client import LeadovaroMCPClient
from leadovaro_mcp_client.adapters.langchain import execute_langchain_tool_call, langchain
from langchain_anthropic import ChatAnthropic
from langchain_core.messages import HumanMessage, ToolMessage

load_dotenv()

async def main():
    client = LeadovaroMCPClient(auth={"token": os.environ["LEADOVARO_TOKEN"]})
    tool_schemas = await client.adapt_for(langchain())

    model = ChatAnthropic(model="claude-sonnet-4-6").bind_tools(tool_schemas)

    messages = [HumanMessage(content="What events do I have today?")]

    while True:
        response = await model.ainvoke(messages)
        messages.append(response)

        if not response.tool_calls:
            break

        for tool_call in response.tool_calls:
            result = await execute_langchain_tool_call(client, tool_call)
            messages.append(ToolMessage(
                content=str(result),
                tool_call_id=tool_call["id"],
            ))

    print(messages[-1].content)
    await client.close()

asyncio.run(main())

Production Configuration​

Lock to a Toolkit​

For production agents, scope to a specific toolkit:

client = LeadovaroMCPClient(
    auth={"token": os.environ["LEADOVARO_TOKEN"]},
    leadovaro_profile=os.environ.get("LEADOVARO_PROFILE_ID"),
)

When a profile is specified, the session is locked by default — the agent cannot switch toolkits or modify its own guardrails. This prevents prompt injection attacks from escaping the defined tool scope.

Reference Implementation​

langchain-nexus-reference-implementation

Complete implementation with FastAPI chat UI, streaming responses, and production patterns

Next Steps​

LangChain.js

JavaScript LangGraph integration using @civic/mcp-client

Agent Deployment

Production deployment guide: profile locking, URL params, authentication

Guardrails

Constrain what tools your LangGraph agent can use

Audit Trail

Query what your agent did via Leadovaro Chat

Get Credentials

Token generation and URL parameter reference