# How to integrate Persistiq MCP with LangChain

```json
{
  "title": "How to integrate Persistiq MCP with LangChain",
  "toolkit": "Persistiq",
  "toolkit_slug": "persistiq",
  "framework": "LangChain",
  "framework_slug": "langchain",
  "url": "https://composio.dev/toolkits/persistiq/framework/langchain",
  "markdown_url": "https://composio.dev/toolkits/persistiq/framework/langchain.md",
  "updated_at": "2026-05-12T10:21:50.640Z"
}
```

## Introduction

This guide walks you through connecting Persistiq to LangChain using the Composio tool router. By the end, you'll have a working Persistiq agent that can send personalized cold emails to new leads, create a follow-up sequence for prospects, log a completed sales call as a task through natural language commands.
This guide will help you understand how to give your LangChain agent real control over a Persistiq account through Composio's Persistiq MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Persistiq with

- [OpenAI Agents SDK](https://composio.dev/toolkits/persistiq/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/persistiq/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/persistiq/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/persistiq/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/persistiq/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/persistiq/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/persistiq/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/persistiq/framework/cli)
- [Google ADK](https://composio.dev/toolkits/persistiq/framework/google-adk)
- [Vercel AI SDK](https://composio.dev/toolkits/persistiq/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/persistiq/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/persistiq/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/persistiq/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Get and set up your OpenAI and Composio API keys
- Connect your Persistiq project to Composio
- Create a Tool Router MCP session for Persistiq
- Initialize an MCP client and retrieve Persistiq tools
- Build a LangChain agent that can interact with Persistiq
- 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 Persistiq MCP server, and what's possible with it?

The Persistiq MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your PersistIQ account. It provides structured and secure access to your sales automation workflows, so your agent can perform actions like managing campaigns, sending personalized emails, creating and updating leads, and automating sales tasks on your behalf.
- Personalized email campaign management: Let your agent create, schedule, and manage outbound email sequences to engage prospects at scale.
- Lead and contact automation: Seamlessly add, update, or remove leads and contacts, ensuring your sales pipeline is always fresh and accurate.
- Automated task handling: Enable your agent to create, update, or complete tasks, helping your team stay on top of follow-ups and to-dos.
- Activity tracking and reporting: Retrieve detailed reports and track engagement metrics, like email opens and replies, to measure campaign effectiveness.
- Sequence step optimization: Adjust and optimize sequence steps or schedules based on real-time insights, maximizing outreach performance.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PERSISTIQ_ADD_LEAD_TO_CAMPAIGN` | Add Lead To Campaign | Tool to add a lead to a specified campaign. Use when you have lead details and a campaign ID to enroll the lead into the campaign. |
| `PERSISTIQ_CREATE_CAMPAIGN` | Create Campaign | Tool to create a new campaign in PersistIQ. Use when you need to set up a new outreach campaign with a specific owner. |
| `PERSISTIQ_CREATE_DNC_DOMAIN` | Create Do Not Contact Domain | Tool to create a Do Not Contact domain. Use when you need to block emails from being sent to addresses at a specific domain without manual approval. |
| `PERSISTIQ_CREATE_LEADS` | Create Leads | Tool to bulk create up to 10 leads. Use when you have multiple new contacts and need optional duplicate-handling. |
| `PERSISTIQ_LIST_CAMPAIGNS` | List Campaigns | Tool to list campaigns. Use when you need to fetch multiple campaigns with optional filters and pagination after setting up your filter criteria. |
| `PERSISTIQ_LIST_DNC_DOMAINS` | List Do Not Contact Domains | Tool to list Do Not Contact domains. Use when you need to retrieve all domains marked as DNC. |
| `PERSISTIQ_LIST_EVENTS` | List Events | Tool to retrieve a list of PersistIQ events. Use when you need to fetch events filtered by group, campaign, lead, user, or time range. |
| `PERSISTIQ_LIST_LEAD_FIELDS` | List Lead Fields | Tool to list all lead fields for your company. Use when you need to retrieve available custom lead fields. |
| `PERSISTIQ_LIST_LEADS` | List Leads | Tool to list leads from PersistIQ. Use when you need to fetch a paginated list of leads, optionally filtering by status or updated_after. |
| `PERSISTIQ_LIST_LEAD_STATUSES` | List lead statuses | Tool to retrieve all lead statuses for your company. Use when you need to list available lead statuses after confirming authentication with PersistIQ. |
| `PERSISTIQ_LIST_USERS` | List Users | Tool to list all non-archived users in your company. Use when you need to retrieve user information including id, name, email, activated status, default_mailbox_id, and salesforce_id. |
| `PERSISTIQ_REMOVE_LEAD_FROM_CAMPAIGN` | Remove Lead From Campaign | Tool to remove a lead from a specified campaign. Use when you need to detach a lead from an existing campaign after confirming both IDs. |
| `PERSISTIQ_UPDATE_LEAD` | Update Lead | Tool to update a lead's information. Use when you need to modify fields (status, tags, or custom attributes) of an existing lead. Call after confirming the lead_id. |
| `PERSISTIQ_VIEW_LEAD` | View Lead | Tool to retrieve a lead by its ID. Use when you have the lead ID and need its detailed information. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Persistiq MCP server is an implementation of the Model Context Protocol that connects your AI agent to Persistiq. It provides structured and secure access so your agent can perform Persistiq operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

No description provided.

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

No description provided.
```python
pip install composio-langchain langchain-mcp-adapters langchain python-dotenv
```

```typescript
npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv
```

### 3. Set up environment variables

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
```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
```

### 4. Import dependencies

No description provided.
```python
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()
```

```typescript
import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
```

### 5. Initialize Composio client

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 Persistiq tools
- Validating that COMPOSIO_USER_ID is also set before proceeding
```python
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")
```

```typescript
const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
```

### 6. Create a Tool Router session

What's happening:
- We're creating a Tool Router session that gives your agent access to Persistiq 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 Persistiq tools as needed
```python
# Create Tool Router session for Persistiq
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['persistiq']
)

url = session.mcp.url
```

```typescript
const session = await composio.create(
    userId as string,
    {
        toolkits: ['persistiq']
    }
);

const url = session.mcp.url;
```

### 7. Configure the agent with the MCP URL

No description provided.
```python
client = MultiServerMCPClient({
    "persistiq-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)
```

```typescript
const client = new MultiServerMCPClient({
    "persistiq-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
```

### 8. Set up interactive chat interface

No description provided.
```python
conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Persistiq 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")
```

```typescript
let conversationHistory: any[] = [];

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

const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
});

rl.prompt();

rl.on('line', async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

    if (!trimmedInput) {
        rl.prompt();
        return;
    }

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
```

### 9. Run the application

No description provided.
```python
if __name__ == "__main__":
    asyncio.run(main())
```

```typescript
main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
```

## Complete Code

```python
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=['persistiq']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "persistiq-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 Persistiq 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())
```

```typescript
import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.COMPOSIO_USER_ID;

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['persistiq']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "persistiq-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Persistiq related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\nSession ended.');
        process.exit(0);
    });
}

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
```

## Conclusion

You've successfully built a LangChain agent that can interact with Persistiq 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 Persistiq MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/persistiq/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/persistiq/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/persistiq/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/persistiq/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/persistiq/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/persistiq/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/persistiq/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/persistiq/framework/cli)
- [Google ADK](https://composio.dev/toolkits/persistiq/framework/google-adk)
- [Vercel AI SDK](https://composio.dev/toolkits/persistiq/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/persistiq/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/persistiq/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/persistiq/framework/crew-ai)

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Autobound](https://composio.dev/toolkits/autobound) - Autobound is an AI-powered sales engagement platform that crafts hyper-personalized outreach and insights. It helps sales teams boost response rates and close more deals through tailored content and recommendations.
- [Better proposals](https://composio.dev/toolkits/better_proposals) - Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.
- [Bidsketch](https://composio.dev/toolkits/bidsketch) - Bidsketch is a proposal software that helps businesses create professional proposals quickly and efficiently. It streamlines the proposal process, saving time while boosting client win rates.
- [Bolna](https://composio.dev/toolkits/bolna) - Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Callerapi](https://composio.dev/toolkits/callerapi) - CallerAPI is a white-label caller identification platform for branded caller ID and fraud prevention. It helps businesses boost customer trust while stopping spam, fraud, and robocalls.
- [Callingly](https://composio.dev/toolkits/callingly) - Callingly is a lead response management platform that automates immediate call and text follow-ups with new leads. It helps sales teams boost response speed and close more deals by connecting seamlessly with CRMs and lead sources.
- [Callpage](https://composio.dev/toolkits/callpage) - Callpage is a lead capture platform that lets businesses instantly connect with website visitors via callback. It boosts lead generation and increases your sales conversion rates.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.
- [Emelia](https://composio.dev/toolkits/emelia) - Emelia is an all-in-one B2B prospecting platform for cold-email, LinkedIn outreach, and prospect research. It streamlines outbound campaigns so you can find, engage, and warm up leads faster.
- [Findymail](https://composio.dev/toolkits/findymail) - Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.
- [Freshdesk](https://composio.dev/toolkits/freshdesk) - Freshdesk is customer support software with ticketing and automation tools. It helps teams streamline helpdesk operations for faster, better customer support.
- [Fullenrich](https://composio.dev/toolkits/fullenrich) - FullEnrich is a B2B contact enrichment platform that aggregates emails and phone numbers from 15+ data vendors. Instantly find and verify lead contact data to boost your outreach.
- [Gatherup](https://composio.dev/toolkits/gatherup) - GatherUp is a customer feedback and online review management platform. It helps businesses boost their reputation by streamlining how they collect and manage customer feedback.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Persistiq MCP?

With a standalone Persistiq MCP server, the agents and LLMs can only access a fixed set of Persistiq tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Persistiq 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 Persistiq tools.

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

Yes, absolutely. You can configure which Persistiq 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 Persistiq data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)