How to integrate Textrazor MCP with LangChain

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Textrazor Logo
LangChain Logo
divider

Introduction

This guide walks you through connecting Textrazor to LangChain using the Composio tool router. By the end, you'll have a working Textrazor agent that can extract named entities from this news article, summarize key phrases in customer reviews, classify support tickets by topic automatically, analyze grammatical structure of this sentence through natural language commands.

This guide will help you understand how to give your LangChain agent real control over a Textrazor account through Composio's Textrazor 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 Textrazor project to Composio
  • Create a Tool Router MCP session for Textrazor
  • Initialize an MCP client and retrieve Textrazor tools
  • Build a LangChain agent that can interact with Textrazor
  • 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 Textrazor MCP server, and what's possible with it?

The Textrazor MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Textrazor account. It provides structured and secure access to advanced natural language processing features, so your agent can extract entities, classify content, analyze grammar, and understand relationships within text—all automatically and at scale.

  • Entity and relationship extraction: Enable your agent to identify and classify people, places, organizations, and relationships from any text, powering intelligent content analysis and knowledge graph building.
  • Text classification and categorization: Automatically categorize documents, articles, or snippets using built-in or custom classifiers, making it easy to sort and organize large volumes of text data.
  • Grammatical and dependency analysis: Let your agent parse sentence structure, analyze grammatical relationships, and build dependency trees to support advanced linguistic understanding and text analytics.
  • Custom dictionary and classifier management: Allow the agent to create and update custom entity dictionaries and classifiers, tailoring analysis to specialized domains or business needs.
  • Phrase extraction and sentiment detection: Extract key phrases, multi-word expressions, and even detect logical entailments or word senses, enabling deeper insights from any written content.

Supported Tools & Triggers

Tools
Get Account InformationThis tool retrieves comprehensive information about a textrazor account, providing essential details about the account's status, usage, and limits.
Classify TextThis tool will classify text into predefined categories using textrazor's classification capabilities.
Manage Custom ClassifiersThis tool manages custom classifiers in textrazor, allowing users to create, update, and manage custom classification categories.
Analyze Dependency TreesThe dependencytreesaction analyzes the grammatical relationships between words in text by creating dependency trees.
Dictionary ManagerThe textrazor dictionary manager tool allows users to create, update, and manage custom entity dictionaries in textrazor.
Extract Entailments from TextThis tool extracts entailments from text using textrazor's api.
Extract Named Entities from TextExtract named entities (people, places, companies, etc.
Extract Phrases from TextThe extractphrases action extracts meaningful phrases from input text using textrazor's phrase extraction capability.
Extract Grammatical Relations from TextThis tool extracts grammatical relations between words in the text.
Extract Word SensesThis tool performs word sense disambiguation on the input text by identifying the most likely meanings of words in context.
Spelling CorrectionThis tool performs spelling correction on the provided text using textrazor's deep spelling correction system.
Analyze Content with TextRazorA comprehensive content analysis tool that combines multiple textrazor extractors to perform a complete analysis of the input text.
Extract Topics from TextA tool to extract topics from text using textrazor's topic extraction capabilities.

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 Textrazor 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 Textrazor tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

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

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Textrazor 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 Textrazor tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "textrazor-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 Textrazor MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Textrazor 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 Textrazor 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 Textrazor 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=['textrazor']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "textrazor-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 Textrazor 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 Textrazor 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 Textrazor MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Textrazor MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Textrazor MCP with Claude Agent SDK

Google ADK

Google ADK

Use Textrazor MCP with Google ADK

Vercel AI SDK

Vercel AI SDK

Use Textrazor MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Textrazor MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Textrazor MCP with LlamaIndex

CrewAI

CrewAI

Use Textrazor MCP with CrewAI

FAQ

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

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

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

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

Used by agents from

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

Book a call↗Get started for free