How to integrate Pinecone MCP with LangChain

Framework Integration Gradient
Pinecone Logo
LangChain Logo
divider

Introduction

This guide walks you through connecting Pinecone to LangChain using the Composio tool router. By the end, you'll have a working Pinecone agent that can query all vectors similar to user question, upsert document embeddings into a namespace, delete vectors from the archive index through natural language commands.

This guide will help you understand how to give your LangChain agent real control over a Pinecone account through Composio's Pinecone MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Pinecone project to Composio
  • Create a Tool Router MCP session for Pinecone
  • Initialize an MCP client and retrieve Pinecone tools
  • Build a LangChain agent that can interact with Pinecone
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

What is the Pinecone MCP server, and what's possible with it?

The Pinecone MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pinecone account. It provides structured and secure access so your agent can perform Pinecone operations on your behalf.

Supported Tools & Triggers

Tools
Cancel Bulk ImportTool to cancel a bulk import operation in Pinecone.
Configure IndexTool to configure an existing Pinecone index, including pod type, replicas, deletion protection, and tags.
Create BackupTool to create a backup of a Pinecone index for disaster recovery and version control.
Create IndexTool to create a Pinecone index with specified configuration.
Create Index with Embedding ModelTool to create a Pinecone index with integrated embedding model for automatic vectorization.
Create Index from BackupTool to create an index from a backup.
Create NamespaceTool to create a namespace within a serverless Pinecone index.
Delete IndexTool to permanently delete a Pinecone index.
Delete NamespaceTool to permanently delete a namespace from a serverless index.
Describe BackupTool to retrieve detailed information about a specific backup.
Describe Bulk ImportTool to describe a specific bulk import operation in Pinecone.
Describe Index StatsTool to get index statistics including vector count per namespace, dimensions, and fullness.
Describe Restore JobTool to get detailed information about a specific restore job in Pinecone.
Generate EmbeddingsTool to generate vector embeddings for input text using Pinecone's hosted embedding models.
Get Model InformationTool to retrieve detailed information about a specific model hosted by Pinecone.
List Bulk ImportsTool to list all recent and ongoing bulk import operations in Pinecone.
List CollectionsTool to list all collections in a Pinecone project (pod-based indexes only).
List Index BackupsTool to list all backups for a specific Pinecone index.
List IndexesTool to list all indexes in a Pinecone project.
List Available ModelsTool to list all available embedding and reranking models hosted by Pinecone.
List NamespacesTool to list all namespaces in a serverless Pinecone index.
List Project BackupsTool to list all backups for indexes in a Pinecone project.
List Restore JobsTool to list all restore jobs for a project with pagination support.
List VectorsTool to list vector IDs in a Pinecone serverless index.
Query VectorsTool to perform semantic search within a Pinecone index using a query vector.
Rerank DocumentsTool to rerank documents by semantic relevance to a query.
Search Records in NamespaceTool to search records within a Pinecone namespace using text, vector, or ID query.
Start Bulk ImportTool to start an asynchronous bulk import of vectors from object storage (S3, GCS, or Azure Blob Storage) into a Pinecone index.
Update VectorTool to update a vector in Pinecone by ID.
Upsert Records to NamespaceTool to upsert text records into a Pinecone namespace.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-langchain langchain-mcp-adapters langchain python-dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • composio-langchain provides Composio integration for LangChain
  • langchain-mcp-adapters enables MCP client connections
  • langchain is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Pinecone functionality through MCP

Initialize Composio client

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Pinecone tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

# Create Tool Router session for Pinecone
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['pinecone']
)

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Pinecone tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Pinecone tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "pinecone-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Pinecone MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Pinecone tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Pinecone related question or task to the agent.\n")

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ['exit', 'quit', 'bye']:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
What's happening:
  • We initialize an empty conversation_history list to maintain context across interactions
  • A while loop continuously accepts user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the ainvoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • We call the main() function using asyncio.run() to start the application

Complete Code

Here's the complete code to get you started with Pinecone and LangChain:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['pinecone']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "pinecone-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Pinecone related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've successfully built a LangChain agent that can interact with Pinecone through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Pinecone MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Pinecone MCP?

With a standalone Pinecone MCP server, the agents and LLMs can only access a fixed set of Pinecone tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Pinecone and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LangChain?

Yes, you can. LangChain fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Pinecone tools.

Can I manage the permissions and scopes for Pinecone while using Tool Router?

Yes, absolutely. You can configure which Pinecone scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Pinecone data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.