How to integrate Neo4J MCP with Autogen

This guide walks you through connecting Neo4J to AutoGen using the Composio tool router. By the end, you'll have a working Neo4J agent that can run cypher queries on customer graph, find shortest paths between accounts, create nodes for new transactions through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Neo4J account through Composio's Neo4J MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Neo4J logoNeo4J
Oauth2BasicApi KeyS2s Oauth2

Neo4J is a graph database platform for storing and querying connected data. Use it to model relationships, run Cypher queries, and power real-time graph analytics.

21 Tools

Introduction

This guide walks you through connecting Neo4J to AutoGen using the Composio tool router. By the end, you'll have a working Neo4J agent that can run cypher queries on customer graph, find shortest paths between accounts, create nodes for new transactions through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Neo4J account through Composio's Neo4J MCP server.

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

Also integrate Neo4J with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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 Neo4J
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Neo4J tools
  • Run a live chat loop where you ask the agent to perform Neo4J 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 Neo4J MCP server, and what's possible with it?

The Neo4J MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Neo4J account. It provides structured and secure access to your Neo4J Aura resources, so your agent can manage database instances, handle snapshots, review projects and users, monitor Graph Data Science sessions, and configure IP filters on your behalf.

  • Aura instance management: Have your agent list, create, inspect, update, or pause Neo4J Aura instances based on your infrastructure needs.
  • Snapshot and recovery operations: Direct your agent to create snapshots, review available backups, inspect snapshot details, or restore an Aura instance from a snapshot.
  • Project and user oversight: Let the agent list Aura projects, inspect project details, review project users, or retrieve information about an organization user.
  • Graph Data Science planning: Instruct your agent to list active Graph Data Science sessions or estimate session size from node counts, relationship counts, and algorithm categories.
  • Network access and agent review: Have your agent list Aura agents, review organization IP filters, or update an existing IP filter.

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 Neo4J 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 Neo4J 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 Neo4J 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 Neo4J session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["neo4j"]
    )
    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 Neo4J 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 Neo4J assistant agent with MCP tools
    agent = AssistantAgent(
        name="neo4j_assistant",
        description="An AI assistant that helps with Neo4J 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 Neo4J 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 Neo4J 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 Neo4J 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 Neo4J 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 Neo4J session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["neo4j"]
    )
    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 Neo4J assistant agent with MCP tools
        agent = AssistantAgent(
            name="neo4j_assistant",
            description="An AI assistant that helps with Neo4J 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 Neo4J 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 Neo4J 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 Neo4J, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Neo4J action and event your agent gets out of the box.

Aggregate Directors Count

Executes a directorsAggregate GraphQL query to count directors in Neo4j.

Create Neo4j Aura Instance

Creates a new Neo4j Aura instance with the specified configuration.

Create Neo4j Aura Snapshot

Create an on-demand snapshot of a Neo4j Aura instance.

Estimate GDS Session Size

Estimate the size of a new GDS (Graph Data Science) session based on node/relationship counts and algorithm categories.

Get Neo4j Aura Instance Details

Retrieves details for a specific Neo4j Aura instance using its unique instance ID.

Get Neo4j Aura Organization User

Retrieves details of a specific user in a Neo4j Aura organization.

Get Neo4j Aura Project Details

Retrieve details of a specific Neo4j Aura project (tenant).

Get Neo4j Aura Project Details (v1beta5)

Retrieve details of a specific Neo4j Aura project (tenant) using the v1beta5 API.

Get Neo4j Aura Snapshot Details

Retrieves details of a specific snapshot for a Neo4j Aura instance.

List Neo4j Aura Agents

List all agents belonging to a specific Neo4j Aura project.

List GDS Sessions

List all Graph Data Science (GDS) sessions for the authenticated Neo4j Aura account.

List Neo4j Aura Instances

Returns a list of Neo4j Aura instances.

List IP Filters

Returns a list of IP filters configured for a Neo4j Aura organization.

List Aura Projects

List all Aura projects (tenants) available to the authenticated user.

List Project Users

List all users in a specific Neo4j Aura project.

List Neo4j Aura Snapshots

Lists available snapshots for a Neo4j Aura instance.

Pause Neo4j Aura Instance

Pauses a Neo4j Aura instance.

Restore Neo4j Aura Instance from Snapshot

Restore a Neo4j Aura instance from a snapshot.

Update Neo4j Aura Instance

Updates a Neo4j Aura instance configuration.

Update Neo4j Aura Instance

Edits the configuration of a Neo4j Aura instance.

Update IP Filter

Updates an existing IP filter for a Neo4j Aura organization.

FRAMEWORKS

How to build Neo4J MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Neo4J MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Neo4J MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Neo4J MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Neo4J MCP with Claude Cowork

Codex logo

Codex

Use Neo4J MCP with Codex

OpenClaw logo

OpenClaw

Use Neo4J MCP with OpenClaw

Hermes logo

Hermes

Use Neo4J MCP with Hermes

CLI logo

CLI

Use Neo4J MCP with CLI

Google ADK logo

Google ADK

Use Neo4J MCP with Google ADK

LangChain logo

LangChain

Use Neo4J MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Neo4J MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Neo4J MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Neo4J MCP with LlamaIndex

CrewAI logo

CrewAI

Use Neo4J MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Neo4J MCP server, the agents and LLMs can only access a fixed set of Neo4J tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Neo4J and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen 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 Neo4J tools.

Yes, absolutely. You can configure which Neo4J 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.

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 Neo4J data and credentials are handled as safely as possible.

Start with Neo4J.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Neo4J tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies