How to integrate Dovetail MCP with Claude Agent SDK

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Dovetail logo
Claude Agent SDK logo
divider

Introduction

This guide walks you through connecting Dovetail to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Dovetail agent that can summarize all data points for project x, create a new insight from interview notes, list every contact added this month through natural language commands.

This guide will help you understand how to give your Claude Agent SDK agent real control over a Dovetail account through Composio's Dovetail MCP server.

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

Also integrate Dovetail with

TL;DR

Here's what you'll learn:
  • Get and set up your Claude/Anthropic and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Dovetail
  • Configure an AI agent that can use Dovetail as a tool
  • Run a live chat session where you can ask the agent to perform Dovetail operations

What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.

Key features include:

  • Native MCP Support: Built-in support for Model Context Protocol servers
  • Permission Modes: Control tool execution permissions
  • Streaming Responses: Real-time response streaming for interactive applications
  • Context Manager: Clean async context management for sessions

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

The Dovetail MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Dovetail account. It provides structured and secure access to your research workspace, so your agent can perform actions like creating insights, managing contacts, organizing channels, and retrieving research notes on your behalf.

  • Automated insight creation: Let your agent synthesize findings and store new insights in your Dovetail projects, streamlining your research analysis workflow.
  • Channel and topic management: Easily create, organize, or delete channels and topics to keep your research data structured and accessible.
  • Contact management and retrieval: Automatically add new research contacts or list all contacts in your workspace for better respondent tracking.
  • Research note access: Ask your agent to fetch detailed information about specific notes, giving you instant access to key research materials.
  • Data point recording and classification: Capture and categorize new data points within channels, ensuring every piece of feedback or observation is logged and ready for analysis.

Supported Tools & Triggers

Tools
Create ChannelCreates a new channel in Dovetail to organize and collect feedback data.
Create ContactTool to create a new contact in Dovetail.
Create DataTool to create a data item in a Dovetail project with text content, title, and/or structured fields.
Create Data PointTool to create a data point within a channel.
Create DocTool to create a doc in a Dovetail project with text content, title and/or custom fields.
Create InsightCreates a new insight in Dovetail to store synthesized research findings, observations, or conclusions.
Create NoteTool to create a note in a Dovetail project with text content, title and/or custom fields.
Create ProjectTool to create a new project in your Dovetail workspace.
Create TopicTool to create a new topic in a Dovetail channel.
Delete ChannelTool to delete an existing channel.
Delete DataTool to delete an existing data item.
Delete DocTool to delete an existing doc.
Delete InsightTool to delete an existing insight.
Delete NoteTool to delete an existing note.
Delete TopicTool to delete an existing topic.
Export DataTool to export data in HTML or Markdown format.
Export DocTool to export a doc in HTML or Markdown format.
Export InsightTool to export an insight in HTML or Markdown format.
Export NoteTool to export a note from Dovetail in HTML or Markdown format.
Get ContactTool to retrieve details of a specific contact.
Get DataTool to retrieve details of a specific data item by ID.
Get DocTool to retrieve details of a specific doc by ID.
Get FileTool to retrieve details of a specific file by its ID.
Get FolderTool to retrieve details of a specific folder.
Get InsightTool to retrieve details of a specific insight by ID.
Get NoteTool to retrieve details of a specific note.
Get ProjectTool to retrieve details of a specific project.
Get Token InfoRetrieves information about the current API token, including its unique identifier and the associated workspace subdomain.
Import Data FileTool to import a public URL of a file as new data in Dovetail.
Import Doc FileTool to import a public file URL as a new doc in Dovetail.
Import Insight from FileTool to import a file from a public URL as a new insight in Dovetail.
Import Note FileTool to import a file from a public URL as a new note in Dovetail.
List ContactsRetrieves a paginated list of contacts from a Dovetail workspace.
List DataTool to list data items in Dovetail.
List DocsTool to list docs in a Dovetail workspace with optional filtering, sorting, and pagination.
List FoldersTool to get a list of folders associated with a workspace.
List HighlightsList highlights from your Dovetail workspace with optional filtering and pagination.
List InsightsTool to get a list of insights associated with a workspace.
List NotesList notes in Dovetail workspace with optional pagination and sorting.
List ProjectsTool to list all projects in Dovetail.
List TagsList all tags in the authenticated Dovetail workspace.
List User DocsTool to get a list of docs associated with a user in Dovetail.
List User InsightsList personal insights for a user in Dovetail.
Magic SearchTool to perform a magic search across workspace data.
Update ChannelTool to update an existing channel's title or context.
Update ContactTool to update an existing contact in Dovetail.
Update DataTool to update a data item in Dovetail.
Update DocTool to update a doc in Dovetail.
Update InsightUpdates an existing insight in Dovetail, allowing you to modify the title and custom fields.
Update NoteTool to update an existing note in Dovetail.
Update TopicTool to update an existing topic.

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

Before starting, make sure you have:
  • Composio API Key and Claude/Anthropic API Key
  • Primary know-how of Claude Agents SDK
  • A Dovetail account
  • Some knowledge of Python

Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
  • Go to the Anthropic Console and create an API key. You'll need credits to use the models.
  • 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

pip install composio-anthropic claude-agent-sdk python-dotenv

Install the Composio SDK and the Claude Agents SDK.

What's happening:

  • composio-anthropic provides Composio integration for Anthropic
  • claude-agent-sdk is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID identifies the user for session management
  • ANTHROPIC_API_KEY authenticates with Anthropic/Claude

Import dependencies

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()
What's happening:
  • We're importing all necessary libraries including the Claude Agent SDK and Composio
  • The load_dotenv() function loads environment variables from your .env file
  • This setup prepares the foundation for connecting Claude with Dovetail functionality

Create a Composio instance and Tool Router session

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Dovetail
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["dovetail"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")
What's happening:
  • The function checks for the required COMPOSIO_API_KEY environment variable
  • We're creating a Composio instance using our API key
  • The create method creates a Tool Router session for Dovetail
  • The returned url is the MCP server URL that your agent will use

Configure Claude Agent with MCP

# Configure remote MCP server for Claude
options = ClaudeAgentOptions(
    permission_mode="bypassPermissions",
    mcp_servers={
        "composio": {
            "type": "http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    },
    system_prompt="You are a helpful assistant with access to Dovetail tools via Composio.",
    max_turns=10
)
What's happening:
  • We're configuring the Claude Agent options with the MCP server URL
  • permission_mode="bypassPermissions" allows the agent to execute operations without asking for permission each time
  • The system prompt instructs the agent that it has access to Dovetail
  • max_turns=10 limits the conversation length to prevent excessive API usage

Create client and start chat loop

# Create client with context manager
async with ClaudeSDKClient(options=options) as client:
    print("\nChat started. Type 'exit' or 'quit' to end.\n")

    # Main chat loop
    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit"}:
            print("Goodbye!")
            break

        # Send query
        await client.query(user_input)

        # Receive and print response
        print("Claude: ", end="", flush=True)
        async for message in client.receive_response():
            if hasattr(message, "content"):
                for block in message.content:
                    if hasattr(block, "text"):
                        print(block.text, end="", flush=True)
        print()
What's happening:
  • The Claude SDK client is created using the async context manager pattern
  • The agent processes each query and streams the response back in real-time
  • The chat loop continues until the user types 'exit' or 'quit'

Run the application

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())
What's happening:
  • This entry point runs the async chat_with_remote_mcp() function using asyncio.run()
  • The application will start, create the MCP connection, and begin the interactive chat session

Complete Code

Here's the complete code to get you started with Dovetail and Claude Agent SDK:

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Dovetail
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["dovetail"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")

    # Configure remote MCP server for Claude
    options = ClaudeAgentOptions(
        permission_mode="bypassPermissions",
        mcp_servers={
            "composio": {
                "type": "http",
                "url": url,
                "headers": {
                    "x-api-key": os.getenv("COMPOSIO_API_KEY")
                }
            }
        },
        system_prompt="You are a helpful assistant with access to Dovetail tools via Composio.",
        max_turns=10
    )

    # Create client with context manager
    async with ClaudeSDKClient(options=options) as client:
        print("\nChat started. Type 'exit' or 'quit' to end.\n")

        # Main chat loop
        while True:
            user_input = input("You: ").strip()
            if user_input.lower() in {"exit", "quit"}:
                print("Goodbye!")
                break

            # Send query
            await client.query(user_input)

            # Receive and print response
            print("Claude: ", end="", flush=True)
            async for message in client.receive_response():
                if hasattr(message, "content"):
                    for block in message.content:
                        if hasattr(block, "text"):
                            print(block.text, end="", flush=True)
            print()

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

Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Dovetail through Composio's Tool Router.

Key features:

  • Native MCP support through Claude's agent framework
  • Streaming responses for real-time interaction
  • Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Dovetail MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Dovetail MCP with OpenAI Agents SDK

Claude Code logo

Claude Code

Use Dovetail MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Dovetail MCP with Claude Cowork

Codex logo

Codex

Use Dovetail MCP with Codex

OpenClaw logo

OpenClaw

Use Dovetail MCP with OpenClaw

Hermes logo

Hermes

Use Dovetail MCP with Hermes

CLI logo

CLI

Use Dovetail MCP with CLI

Google ADK logo

Google ADK

Use Dovetail MCP with Google ADK

LangChain logo

LangChain

Use Dovetail MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Dovetail MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Dovetail MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Dovetail MCP with LlamaIndex

CrewAI logo

CrewAI

Use Dovetail MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Claude Agent SDK?

Yes, you can. Claude Agent SDK 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 Dovetail tools.

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

Yes, absolutely. You can configure which Dovetail 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 Dovetail 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.

Get started for freeGet a demo↗