How to integrate Render MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Render logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Render to AutoGen using the Composio tool router. By the end, you'll have a working Render agent that can deploy latest code to staging service, restart production web service now, get current status of all services through natural language commands.

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

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

Also integrate Render with

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

The Render MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Render account. It provides structured and secure access to your cloud infrastructure, so your agent can perform actions like deploying applications, managing services, monitoring site health, restarting instances, and scaling resources on your behalf.

  • Automated application deployment: Instantly deploy new web apps or services without manual steps, letting your agent handle setup and rollouts.
  • Service monitoring and status checks: Ask your agent to check the health and uptime of your apps or services, so you’re always up to speed on what’s running smoothly—and what’s not.
  • Instance management and restarts: Enable your agent to restart, stop, or scale up/down your running services to quickly respond to changes or issues.
  • Resource scaling and configuration: Let your agent adjust resource allocations, increasing or decreasing capacity based on current needs or traffic spikes.
  • Error diagnostics and log retrieval: Have your agent fetch logs or error reports to help troubleshoot issues before they become major problems.

Supported Tools & Triggers

Tools
Add Header RuleTool to add a custom HTTP header rule to a Render service.
Add or Update Secret FileTool to add or update a secret file for a Render service.
Add Resources to EnvironmentTool to add resources to a Render environment.
Add RouteTool to add redirect or rewrite rules to a Render service.
Create Custom DomainTool to add a custom domain to a Render service.
Create Environment GroupTool to create a new environment group.
Create EnvironmentTool to create a new environment within a Render project.
Create Postgres InstanceTool to create a new Postgres instance on Render.
Create Registry CredentialTool to create a registry credential.
Delete Environment Group VariableTool to remove an environment variable from an environment group.
Delete Environment Group Secret FileTool to remove a secret file from an environment group.
Delete EnvironmentTool to delete a specified environment.
Delete Key ValueTool to delete a Key Value instance.
Delete Owner Log StreamTool to delete a log stream for an owner.
Delete Owner Metrics StreamTool to delete a metrics stream for a workspace.
Delete Registry CredentialTool to delete a registry credential.
Delete Secret FileTool to delete a secret file from a Render service.
Delete ServiceTool to delete a service.
Disconnect BlueprintTool to disconnect a blueprint from your Render account.
Get Active ConnectionsTool to get active connection count metrics for Render resources.
Get Bandwidth SourcesTool to get bandwidth usage breakdown by traffic source.
Get CPU UsageTool to retrieve CPU usage metrics for Render resources.
Get CPU LimitTool to retrieve CPU limit metrics for Render resources.
Get Disk CapacityTool to get disk capacity metrics for Render resources.
Get Disk UsageTool to retrieve disk usage metrics for Render resources.
Get Instance CountTool to get instance count metrics for Render resources.
Get Memory UsageTool to get memory usage metrics for one or more resources.
Get Memory LimitTool to get memory limit metrics for Render resources over a specified time range.
Get Memory TargetTool to get memory target metrics for Render resources.
Get UserTool to get the authenticated user.
Link Service to Environment GroupTool to link a service to an environment group.
List Application Filter ValuesTool to list queryable instance values for application metrics.
List BlueprintsTool to list all blueprints.
List DeploysTool to list recent deploys for a Render service with pagination and filtering.
List DisksTool to list all disks.
List Environment GroupsTool to list environment groups.
List EnvironmentsTool to list environments for a project.
List Environment Variables for ServiceTool to list all environment variables configured directly on a Render service (with pagination).
List InstancesTool to list instances of a service.
List Key Value InstancesTool to list all Key Value instances.
List LogsTool to list logs for a specific workspace and resource.
List Log Label ValuesTool to list log label values for a workspace.
List Maintenance RunsTool to list maintenance runs.
List Notification OverridesTool to list notification overrides for services.
List Workspace MembersTool to list workspace members.
List OwnersTool to list owners (users and teams).
List Postgres InstancesTool to list Postgres instances.
List Postgres ExportsTool to list all exports for a Postgres instance.
List PostgreSQL UsersTool to list PostgreSQL user credentials for a Render PostgreSQL database instance.
List ProjectsList Projects
List Registry CredentialsTool to list registry credentials.
List Resource Log StreamsTool to list resource log stream overrides.
List RoutesTool to list redirect/rewrite rules for a service.
List Secret FilesTool to list secret files for a Render service.
List ServicesTool to list all services.
List Task RunsTool to list task runs.
List TasksTool to list tasks.
List WebhooksTool to list all webhooks.
List WorkflowsTool to list workflows.
List Workflow VersionsTool to list workflow versions.
Restart ServiceTool to restart a service.
Resume ServiceTool to resume a suspended service.
Retrieve Custom DomainTool to retrieve a specific custom domain for a service.
Retrieve deployRetrieve deploy
Retrieve Environment GroupTool to retrieve a specific environment group by ID.
Retrieve Environment VariableTool to retrieve a specific environment variable from a Render environment group.
Retrieve Environment Group Secret FileTool to retrieve secret file from an environment group.
Retrieve Environment VariableTool to retrieve a specific environment variable from a Render service.
Retrieve OwnerTool to retrieve a specific owner (workspace) by ID.
Retrieve Owner Notification SettingsTool to retrieve notification settings for a specific owner (workspace).
Retrieve Postgres InstanceTool to retrieve a specific Postgres instance.
Retrieve ProjectTool to retrieve a specific project by ID.
Retrieve Registry CredentialTool to retrieve a registry credential by ID.
Retrieve Secret FileTool to retrieve a secret file from a Render service.
Retrieve ServiceTool to retrieve a specific service by ID.
Stream Task Runs EventsTool to stream real-time task run events via Server-Sent Events (SSE).
Subscribe to LogsTool to subscribe to real-time logs via WebSocket connection.
Suspend ServiceTool to suspend a service.
Trigger DeployTool to trigger a new deploy for a specified service.
Update Environment GroupTool to update an environment group's name.
Update Environment Group VariableTool to add or update an environment variable in an environment group.
Update Environment Group Secret FileTool to add or update a secret file in an environment group.
Update Environment VariableTool to add or update an environment variable for a Render service.
Update Environment Variables for ServiceTool to update environment variables for a Render service.
Update Header RulesTool to replace all header rules for a Render service.
Update Owner Log StreamTool to update log stream configuration for an owner.
Update Owner Notification SettingsTool to update notification settings for a specific owner (workspace).
Update Postgres InstanceTool to update a Postgres instance configuration.
Update ProjectTool to update a project's name.
Update Registry CredentialTool to update a registry credential.
Update Resource Log StreamTool to update log stream override for a resource.
Update RoutesTool to update redirect/rewrite rules for a service.
Update Secret Files for ServiceTool to update secret files for a Render service.
Update ServiceTool to update a service configuration.
Verify Custom DomainTool to verify DNS configuration for a custom domain.

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

Prerequisites

You will need:

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

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

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 Render via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Render connections to use

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 Render session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["render"]
    )
    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 Render tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Render assistant agent with MCP tools
    agent = AssistantAgent(
        name="render_assistant",
        description="An AI assistant that helps with Render 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 Render tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Render 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 Render 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 Render 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 Render session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["render"]
    )
    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 Render assistant agent with MCP tools
        agent = AssistantAgent(
            name="render_assistant",
            description="An AI assistant that helps with Render 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 Render 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 Render 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 Render, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Render MCP Agent with another framework

FAQ

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

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

Can I use Tool Router MCP with Autogen?

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 Render tools.

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

Yes, absolutely. You can configure which Render 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 Render 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.