Skip to main content

​
Overview

LangChain can connect to Observee’s MCP (Model Context Protocol) server using the langchain-mcp-adapters package. This enables your LangChain applications to access Observee’s tool ecosystem through the familiar LangChain interface.

​
Prerequisites

Before getting started, ensure you have:
  • Python 3.10 or later installed
  • Required packages installed: 
    pip install langchain-mcp-adapters langgraph langchain
  • Your Observee client ID for identifying your customer
  • Your Observee API key for authentication
  • OpenAI API key or other LLM provider credentials

​
Example: Creating a React Agent with Observee Tools

This example shows how to create a simple React agent that can use tools from your Observee MCP server: 
from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent

# Configure the MCP client to connect to Observee
# Replace {your_client_id} with your actual client ID from the Observee dashboard
client = MultiServerMCPClient(
    {
        "observee": {
            "transport": "streamable_http",
            "url": "https://mcp.observee.ai/mcp?client_id={your_client_id}",
            "headers": {
                "Authorization": "Bearer {observee_api_key}"  # Replace with your API key
            },
        }
    }
)

# Get all available tools from Observee
tools = await client.get_tools()

# Create a React agent with the tools
agent = create_react_agent("openai:gpt-4.1", tools)

# Use the agent - it will automatically use appropriate Observee tools
response = await agent.ainvoke({
    "messages": "check my latest emails and add to my sheets"
})

print(response)

​
Learn More