How to integrate Coda MCP with Autogen

This guide walks you through connecting Coda to AutoGen using the Composio tool router. By the end, you'll have a working Coda agent that can duplicate your project tracker document, add a new permission for this doc, export the content of the roadmap page through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Coda account through Composio's Coda 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
Coda logoCoda
Api Key

Coda is a collaborative workspace that turns documents into powerful tools for teams. It's designed to boost productivity by combining docs, spreadsheets, and apps in a single platform.

109 Tools4 Triggers

Introduction

This guide walks you through connecting Coda to AutoGen using the Composio tool router. By the end, you'll have a working Coda agent that can duplicate your project tracker document, add a new permission for this doc, export the content of the roadmap page through natural language commands.

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

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

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

The Coda MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Coda account. It provides structured and secure access to your workspaces and docs, so your agent can automate Coda document creation, manage permissions, export content, and streamline your team’s productivity tools—all on your behalf.

  • Automated document and page creation: Instruct your agent to create new Coda documents or pages, duplicate existing docs, and organize content structure with just a prompt.
  • Flexible permission and sharing management: Have your agent add or modify user, workspace, or global permissions, so you’re always in control of who can view or edit your docs.
  • Seamless content export and status tracking: Let your agent initiate exports of Coda pages and check the progress, making it easy to share or archive important information.
  • Custom domain and publishing management: Direct your agent to add custom domains to published docs or manage categories and makers for Coda packs, keeping your workspace organized and discoverable.
  • Pack release and workspace enhancements: Ask your agent to create new pack releases or manage integrations, helping teams extend Coda’s power without repetitive manual steps.

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

Supported Tools and Triggers

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

Add a category for pack

Add a publishing category for a given pack.

Add a maker for pack

Add a maker to a Pack.

Add a permission for pack

Create or modify permissions for a given Pack.

Add custom domain

Add a custom domain to a published doc.

Add permission

Adds a new permission to the doc.

Begin content export

Initiate an asynchronous export of page content in HTML or Markdown format.

Content export status

Check the status of a page content export operation.

Copy Document

Creates a copy of an existing Coda document.

Create a new pack release

Creates a new Pack release based on an existing Pack version.

Create a page

Create a new page in a doc.

Create doc

Creates a new Coda doc, optionally copying an existing doc.

Create Folder

Creates a new folder in a Coda workspace.

Create Pack

Creates a new Pack in Coda.

Create Pack Invitation

Create an invitation for a user to access a Pack.

Delete a category for pack

Delete a publishing category for a given pack.

Delete a maker for pack

Removes a maker from a Pack's maker list.

Delete a page

Deletes the specified page.

Delete a permission for pack

Delete user, workspace, or global permissions for a given Pack.

Delete doc

Permanently deletes a Coda doc.

Delete Folder

Tool to delete a folder in Coda.

Delete multiple rows

Deletes multiple rows from a Coda table or view.

Delete pack

Delete a given Pack.

Delete Pack listing draft

Delete the listing draft for a Pack, discarding any unsaved changes.

Delete Page Content

Tool to delete content from a Coda page.

Delete permission

Deletes an existing permission from a Coda document.

Delete row

Deletes the specified row from the table or view.

Deletes a custom domain

Deletes a custom domain from a published doc.

Fetch grouped logs by pack org root ingestion id

Retrieve the grouped logs of a Pack ingestion for debugging purposes.

Fetch ingestion executions for pack

Retrieve the ingestion execution ids of a root ingestion for debugging purpose.

Get acl settings

Returns settings associated with ACLs for this Coda doc.

Get a column

Returns detailed information about a specific column in a Coda table.

Get a control

Returns info on a control.

Get a formula

Returns info on a formula.

Get analytics last updated day

Returns days based on Pacific Standard Time when analytics were last updated.

Get a page

Returns details about a page.

Get a row

Retrieves detailed information about a specific row in a Coda table, including all cell values, metadata (creation/update timestamps), and parent table information.

Get Pack details by ID

Retrieves detailed information about a specific Coda Pack by its ID.

Get a table

Returns details about a specific table or view.

Get detailed listing information for a pack

Get comprehensive public listing information for a Coda Pack.

Get doc analytics summary

Returns aggregated analytics summary data across documents, including session counts, installs, copies, reads, and conversions.

Get doc categories

Retrieves the list of all available doc categories in Coda.

Get folder

Tool to get metadata about a Coda folder.

Get info about a doc

Retrieves comprehensive metadata for a specific Coda document.

Get mutation status

Checks whether an asynchronous mutation operation has been applied to a Coda document.

Get pack analytics summary

Returns summarized analytics data for Packs the user can edit.

Gets custom doc domains providers

Identifies the domain registrar/provider for a given domain name by performing a DNS lookup.

Get sharing metadata

Returns metadata associated with sharing for this Coda doc.

Gets the json schema for pack configuration

Retrieves the JSON Schema that defines the configuration options available for a specific Coda Pack.

Get the difference between two pack versions

Gets information about the difference between the specified previous version and next version of a Pack.

Get the next valid version for a pack

Get the next valid version number for a Pack based on the proposed metadata.

Get the source code for a pack version

Retrieves temporary download URLs for the source code files of a specific Pack version.

Get user info

Returns basic info about the current user.

List available docs

Returns a list of Coda docs accessible by the user, and which they have opened at least once.

List categories for pack

List all publishing categories associated with a specific Coda Pack.

List columns

Returns a list of columns in a table.

List controls

Returns a list of controls in a Coda doc.

List custom doc domains

List all custom domains configured for a published Coda doc.

List doc analytics

Returns analytics data for accessible documents.

List featured docs for a pack

Returns a list of featured docs for a Pack.

List Folders

Tool to list folders accessible by the user.

List formulas

Returns a list of named formulas in a Coda doc.

List makers for pack

List makers for a given pack.

List pack analytics

Returns analytics data for Packs the user can edit.

List pack formula analytics

Returns analytics data for Pack formulas.

List packs

Get the list of accessible Packs.

List page analytics

Returns page-level analytics data for pages within a document.

List Page Content

Tool to list page content.

List pages

Returns a list of pages in a Coda doc.

List permissions

Returns a list of permissions for this Coda doc.

List permissions for a pack

Get user, workspace, and/or global permissions for a given Pack.

List table rows

Retrieves rows from a specific table within a Coda document.

List tables

Returns a list of tables in a Coda doc.

List the pack listings accessible to a user

Get listings of public Packs and Packs created by you.

List the releases for a pack

Get the list of releases of a Pack.

List the versions for a pack

Get the list of versions of a Pack.

List User Pack Invitations

Tool to get pending Pack invitations for the authenticated user.

List workspace roles

Returns a list of the counts of users over time by role for the workspace.

List workspace users

Returns a list of members in the given workspace.

Pack asset upload complete

Notify Coda that the Pack asset upload to S3 is complete.

Pack source code upload complete

Notify Coda that the Pack source code upload to S3 is complete.

Pack version upload complete

Mark a Pack version upload as complete to finalize the Pack version creation.

Patch the system connection credentials of the pack

Patch the system connection credentials of the Pack.

Publish doc

Update publish settings for a doc.

Push a button

Pushes a button on a row in a table.

Register pack version

Registers a new Pack version and obtains a signed upload URL.

Resolve browser link

Given a browser link to a Coda object, attempts to find it and return metadata that can be used to get more info on it.

Retrieve the grouped logs of a pack

Retrieve grouped execution logs for a Pack in a specific Coda document.

Retrieve the information for a specific log

Retrieve detailed information for a specific log entry from a Pack ingestion.

Retrieve the logs of a ingestion

Retrieve the logs of a Ingestion for debugging purpose.

Retrieve the logs of a pack

Retrieve the execution logs of a Pack within a specific document for debugging purposes.

Retrieve the oauth configuration of the pack

Retrieve the OAuth configuration of the Pack for display purpose.

Retrieve the system connection metadata of the pack

Retrieve the system connection metadata of a Pack.

Search principals

Search for users and groups (principals) that a Coda document can be shared with.

Set the oauth configurations of the pack

Set OAuth2 client credentials (client ID, secret, redirect URI) for a Pack.

Set the system connection credentials of the pack

Set the system connection credentials of the Pack.

Trigger automation

Triggers a webhook-invoked automation in a Coda doc.

Unpublish doc

Unpublishes a Coda document, removing it from public access.

Update acl settings

Update access control list (ACL) settings for a Coda document.

Update an existing Pack release

Update the release notes of an existing Pack release.

Update a page

Update properties for a page.

Update doc

Updates metadata for a Coda document, including its title and icon.

Update featured docs for a pack

Create or replace the featured docs for a Pack.

Update Folder

Tool to update folder metadata in Coda.

Update pack

Update an existing Pack for non-versioned fields.

Updates a custom domain

Updates properties of a document's custom domain.

Updates user role

Updates the workspace user role of a user that matches the parameters.

Upload a pack asset

Request a signed s3 URL to upload your Pack asset.

Upload pack source code

Request a signed s3 URL to upload your Pack source code.

Insert/Update Rows in Coda Table

This tool allows you to insert new rows into a Coda table or update existing ones based on specified key columns.

FRAMEWORKS

How to build Coda MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Coda MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Coda MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Coda MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Coda MCP with Claude Cowork

Codex logo

Codex

Use Coda MCP with Codex

OpenClaw logo

OpenClaw

Use Coda MCP with OpenClaw

Hermes logo

Hermes

Use Coda MCP with Hermes

CLI logo

CLI

Use Coda MCP with CLI

Google ADK logo

Google ADK

Use Coda MCP with Google ADK

LangChain logo

LangChain

Use Coda MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Coda MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Coda MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Coda MCP with LlamaIndex

CrewAI logo

CrewAI

Use Coda MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Coda.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Coda 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