SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Espocrm MCP with Autogen

Connect Autogen to Espocrm MCP. Show your espocrm user profile details, list all roles and permissions for your account, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Espocrm logoEspocrm
Api Key

EspoCRM is an open-source web application for managing customer relationships. It helps businesses organize contacts, track leads, and streamline their sales process.

16 Tools

Introduction

This guide walks you through connecting Espocrm to AutoGen using the Composio tool router. By the end, you'll have a working Espocrm agent that can create and update records, link related records, follow records and post stream notes, upload attachments, and check currency rates through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Espocrm with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Espocrm
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Espocrm tools
  • Run a live chat loop where you ask the agent to perform Espocrm operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The Espocrm MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Espocrm account. It provides structured and secure access to your CRM data, so your agent can perform actions like retrieving user profiles, accessing system configuration, and managing user preferences on your behalf.

  • Retrieve current session user details: Allow your agent to securely fetch information about the logged-in user, including access tokens, roles, and preferences for personalized automation.
  • Access EspoCRM system metadata: Instantly pull system configuration, user details, permissions, and translation data to help your agent understand and navigate your CRM environment.
  • Automate user-specific tasks: Enable your agent to tailor workflows and responses based on the authenticated user’s profile and preferences.
  • Discover CRM capabilities programmatically: Let your agent analyze available modules, user permissions, and ACL settings to ensure actions are compliant and context-aware.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Espocrm account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Espocrm via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Espocrm connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Espocrm session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["espocrm"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Espocrm tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Espocrm assistant agent with MCP tools
    agent = AssistantAgent(
        name="espocrm_assistant",
        description="An AI assistant that helps with Espocrm operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Espocrm tools from the workbench
8

Run the interactive chat loop

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

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

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

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Espocrm tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Espocrm and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Espocrm session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["espocrm"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Espocrm assistant agent with MCP tools
        agent = AssistantAgent(
            name="espocrm_assistant",
            description="An AI assistant that helps with Espocrm operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

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

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

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

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

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

Conclusion

You now have an Autogen assistant wired into Espocrm through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Espocrm, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Espocrm action and event your agent gets out of the box.

Create Record

Create a record for any standard or custom EspoCRM entity type.

Download Attachment

Download an EspoCRM attachment by attachment record ID.

Follow Record

Follow an EspoCRM record so its updates appear in the user's stream.

Get App User

Tool to retrieve current user data including token, ACL, and preferences.

Get Currency Rates

Retrieve the currency rates configured in EspoCRM.

Get Labels

Retrieve all EspoCRM labels in the user or system default language.

Get Metadata

Retrieve available EspoCRM application metadata or one metadata path.

Get Record

Retrieve one standard or custom EspoCRM entity record by its ID.

List Records

List one page of records for any standard or custom EspoCRM entity type.

List Record Stream

List one page of stream notes for a standard or custom EspoCRM record.

List Related Records

List one page of records connected to a source record through a named link.

List Stream

List one page of stream notes visible to the current EspoCRM user.

Post Stream Note

Post a note to an EspoCRM record stream, optionally with attachments.

Relate Records

Relate one or more existing records through a named EspoCRM link.

Update Record

Partially update any standard or custom EspoCRM entity record.

Upload Attachment

Upload a file for an EspoCRM File or Attachment-Multiple field.

FRAMEWORKS

How to build Espocrm MCP Agent with another framework

Claude Code logo

Claude Code

Use Espocrm MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Espocrm MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Espocrm MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Espocrm MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Espocrm MCP with Grok Bot

Codex logo

Codex

Use Espocrm MCP with Codex

OpenClaw logo

OpenClaw

Use Espocrm MCP with OpenClaw

Hermes logo

Hermes

Use Espocrm MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Espocrm MCP with Atomic Agent

Google ADK logo

Google ADK

Use Espocrm MCP with Google ADK

LangChain logo

LangChain

Use Espocrm MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Espocrm MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Espocrm MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Espocrm MCP with LlamaIndex

CrewAI logo

CrewAI

Use Espocrm MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Espocrm MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Espocrm.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Espocrm tool your agent needs.Free to start.

Start building