How to integrate Doppler secretops MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Doppler secretops Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Doppler secretops to AutoGen using the Composio tool router. By the end, you'll have a working Doppler secretops agent that can list all recent config changes for project x, rollback staging config to previous version, clone production config to a new branch, lock main config to prevent accidental edits through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Doppler secretops account through Composio's Doppler secretops 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
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Doppler secretops
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Doppler secretops tools
  • Run a live chat loop where you ask the agent to perform Doppler secretops 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 Doppler secretops MCP server, and what's possible with it?

The Doppler secretops MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Doppler secretops account. It provides structured and secure access to your secrets management platform, so your agent can perform actions like auditing activity logs, managing environment configs, rolling back changes, and automating config cloning on your behalf.

  • Fetch activity and config logs: Quickly retrieve detailed activity logs and config change histories to monitor changes and track security events across your Doppler workspace.
  • Rollback and restore configurations: Direct your agent to roll back a config to a previous version, helping you easily undo unwanted or risky changes with confidence.
  • Clone and create branch configs: Automate the cloning of config branches or create new branch configs for different environments and projects, streamlining your secrets management workflows.
  • Config locking and deletion: Secure your critical configs by locking them against unwanted changes or safely deleting obsolete configurations as part of environment cleanup.
  • Retrieve detailed config metadata: Instantly get comprehensive details for any specific config, including project and environment context, to support debugging and compliance tasks.

Supported Tools & Triggers

Tools
Activity Logs ListTool to list workplace activity logs.
Retrieve Activity LogTool to retrieve a single activity log entry by id.
Retrieve Config Log EntryTool to retrieve a specific config log entry.
Config Logs ListTool to list config change logs for a specific config.
Config Logs RollbackTool to rollback a config to a selected log version.
Clone ConfigTool to clone a branch config including all its secrets.
Create Branch ConfigTool to create a branch config.
Configs DeleteTool to delete a config permanently.
Get Config DetailsTool to fetch a config's details.
Lock ConfigTool to lock a config.
Unlock ConfigTool to unlock a config.
Update ConfigTool to modify an existing config.
Revoke Dynamic Secret LeaseTool to revoke a dynamic secret lease.
Create EnvironmentTool to create a new environment.
Environments DeleteTool to delete an environment.
Get Environment DetailsTool to retrieve an environment.
List EnvironmentsTool to list environments in a Doppler project.
Rename EnvironmentTool to rename an environment.
Remove Group MemberTool to remove a member from a group.
Integrations ListTool to list all external integrations.
Invites ListTool to list open workplace invites.
Remove Project MemberTool to remove a member from a project.
Get Project MemberTool to retrieve a project member by type and slug.
Project Permissions ListTool to list project-level permissions.
Get Project RoleTool to retrieve a project role.
Create ProjectTool to create a project.
Projects DeleteTool to delete a project permanently.
List ProjectsTool to list Doppler projects.
Update SecretsTool to update secrets in a config.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Doppler secretops 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 Doppler secretops 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 Doppler secretops 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 Doppler secretops session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["doppler_secretops"]
    )
    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 Doppler secretops 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 Doppler secretops assistant agent with MCP tools
    agent = AssistantAgent(
        name="doppler_secretops_assistant",
        description="An AI assistant that helps with Doppler secretops 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 Doppler secretops 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 Doppler secretops 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 Doppler secretops 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 Doppler secretops and AutoGen:

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

How to build Doppler secretops MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Doppler secretops MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Doppler secretops MCP with Claude Agent SDK

Google ADK

Google ADK

Use Doppler secretops MCP with Google ADK

LangChain

LangChain

Use Doppler secretops MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Doppler secretops MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Doppler secretops MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Doppler secretops MCP with LlamaIndex

CrewAI

CrewAI

Use Doppler secretops MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Doppler secretops MCP?

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

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

Yes, absolutely. You can configure which Doppler secretops 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 Doppler secretops 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.

Book a call↗Get started for free