# How to integrate Rocketlane MCP with Pydantic AI

```json
{
  "title": "How to integrate Rocketlane MCP with Pydantic AI",
  "toolkit": "Rocketlane",
  "toolkit_slug": "rocketlane",
  "framework": "Pydantic AI",
  "framework_slug": "pydantic-ai",
  "url": "https://composio.dev/toolkits/rocketlane/framework/pydantic-ai",
  "markdown_url": "https://composio.dev/toolkits/rocketlane/framework/pydantic-ai.md",
  "updated_at": "2026-05-12T10:24:20.856Z"
}
```

## Introduction

This guide walks you through connecting Rocketlane to Pydantic AI using the Composio tool router. By the end, you'll have a working Rocketlane agent that can create a new onboarding project for acme corp, log two hours to client implementation task, archive completed projects from last quarter through natural language commands.
This guide will help you understand how to give your Pydantic AI agent real control over a Rocketlane account through Composio's Rocketlane MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Rocketlane with

- [OpenAI Agents SDK](https://composio.dev/toolkits/rocketlane/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/rocketlane/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/rocketlane/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/rocketlane/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/rocketlane/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/rocketlane/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/rocketlane/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/rocketlane/framework/cli)
- [Google ADK](https://composio.dev/toolkits/rocketlane/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/rocketlane/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/rocketlane/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/rocketlane/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/rocketlane/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/rocketlane/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- How to set up your Composio API key and User ID
- How to create a Composio Tool Router session for Rocketlane
- How to attach an MCP Server to a Pydantic AI agent
- How to stream responses and maintain chat history
- How to build a simple REPL-style chat interface to test your Rocketlane workflows

## What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.
Key features include:
- Type Safety: Built on Pydantic for automatic data validation
- MCP Support: Native support for Model Context Protocol servers
- Streaming: Built-in support for streaming responses
- Async First: Designed for async/await patterns

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

The Rocketlane MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Rocketlane account. It provides structured and secure access to your onboarding projects, tasks, and customer data, so your agent can perform actions like creating tasks, managing companies, tracking time entries, and handling project organization on your behalf.
- Project and company management: Easily direct your agent to create new projects or companies, retrieve detailed company info, and keep your workspace organized.
- Task creation and deletion: Have your agent add new tasks to any project or swiftly delete outdated tasks using their unique identifiers.
- Time entry tracking: Log time spent on tasks or projects, review details, or delete time entries for accurate billing and reporting.
- Custom field insights: Retrieve all available custom fields or fetch specific field details to tailor onboarding workflows to your needs.
- Project archiving and cleanup: Archive completed projects for future reference or permanently delete projects when they're no longer needed, keeping your workspace tidy.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `ROCKETLANE_ADD_ASSIGNEE_TO_TASK` | Add Assignee To Task | Add assignees to a task by task ID. Assigns one or more users to a specific task. |
| `ROCKETLANE_ADD_FIELD_OPTION` | Add Field Option | Tool to add a new option to a SINGLE_CHOICE or MULTIPLE_CHOICE field. Use when extending dropdown or select field options with a new labeled and colored choice. |
| `ROCKETLANE_ADD_FOLLOWERS_TO_TASK` | Add Followers To Task | Tool to add followers to a task by Id. Use when you need to add team members as followers to track task updates. |
| `ROCKETLANE_ADD_MEMBERS` | Add Members to Project | Tool to add team members to a project using the projectId. Team members are participants from your company who work on projects and deliverables. |
| `ROCKETLANE_ADD_MEMBERS_TO_CONVERSATION` | Add Members to Conversation | Add members to a conversation in Rocketlane. Use this when you need to include additional team members or stakeholders in an existing conversation. |
| `ROCKETLANE_ARCHIVE_PROJECT_BY_ID` | Archive Project by ID | Archives a specific project based on its unique identifier. |
| `ROCKETLANE_CREATE_COMMENT` | Create Comment | Tool to create a comment in Rocketlane. Use when you need to add a comment to a task or project conversation. |
| `ROCKETLANE_CREATE_COMPANY` | Create Company | Creates a new company (account) in Rocketlane. This action allows you to create a new company/account in your Rocketlane workspace. It complements existing company-related actions by providing the ability to register new accounts using the POST /api/v2/companies endpoint. |
| `ROCKETLANE_CREATE_CONVERSATION` | Create Conversation | Creates a new conversation in Rocketlane. Use this to start a conversation associated with a project or other source type. You can specify members, privacy settings, and whether to include all members automatically. |
| `ROCKETLANE_CREATE_FIELD` | Create Field | Tool to create a custom field in Rocketlane. Use when you need to add a new custom field to TASK, PROJECT, PHASE, or USER objects. For SINGLE_CHOICE or MULTIPLE_CHOICE field types, you must provide the options array. |
| `ROCKETLANE_CREATE_PHASE` | Create Phase | Tool to create a new phase in a Rocketlane project. Use when you need to add a new phase to an existing project with specified timeline and configuration. |
| `ROCKETLANE_CREATE_PROJECT` | Create Project | Tool to create a new project in Rocketlane. Use when you need to set up a new project with details like name, customer, owner, dates, and custom fields. |
| `ROCKETLANE_CREATE_SPACE` | Create Space | Creates a new space for a given project in Rocketlane. Use when you need to create a collaborative workspace within a project with specific privacy settings. |
| `ROCKETLANE_CREATE_SPACE_DOCUMENT` | Create Space Document | Tool to create a new space document in Rocketlane. Use when you need to add documents to a project space, either as native Rocketlane documents or embedded links from external sources. |
| `ROCKETLANE_CREATE_TASK` | Create Task | Creates a new task. |
| `ROCKETLANE_CREATE_TIME_ENTRY` | Create Time Entry | Tool to create a new time entry in Rocketlane. This endpoint allows users to log time spent on tasks or projects. It complements the existing ROCKETLANE_GET_TIME_ENTRIES action and enables complete time tracking functionality within the Rocketlane integration. |
| `ROCKETLANE_DELETE_COMMENT_BY_ID` | Delete Comment By ID | Tool to delete a comment by its ID. Use when you need to permanently remove a comment from Rocketlane. |
| `ROCKETLANE_DELETE_CONVERSATION` | Delete Conversation | Tool to delete a conversation by its unique identifier. Use when you need to permanently remove a conversation from Rocketlane. |
| `ROCKETLANE_DELETE_FIELD` | Delete Field | Tool to permanently delete a custom field using its unique identifier. Use when a field is no longer required and should be removed from the system. |
| `ROCKETLANE_DELETE_PHASE` | Delete Phase | Permanently delete a phase from the project using its unique identifier (phaseId). Use when you need to remove a phase that is no longer needed. |
| `ROCKETLANE_DELETE_PROJECT` | Delete Project | This tool allows users to permanently delete a project in Rocketlane. It requires a valid project ID and appropriate permissions (Admins, Super Users, and Project Owners). Note that deletion is irreversible; therefore, consider using archival if future access might be needed. |
| `ROCKETLANE_DELETE_SPACE` | Delete Space | Tool to permanently delete a space from a project by its ID. Use when you need to remove a space from the Rocketlane system. Note: This operation is permanent and cannot be undone. |
| `ROCKETLANE_DELETE_SPACE_DOCUMENT` | Delete Space Document | Tool to permanently delete a space document by its ID. Use when you need to remove a space document from the system. |
| `ROCKETLANE_DELETE_TASK_BY_ID` | Delete Task By ID | Delete a specific task using its unique identifier (taskId). |
| `ROCKETLANE_DELETE_TIME_ENTRY_BY_ID` | Delete Time Entry by ID | Delete a specific time entry using its unique identifier (timeEntryId). |
| `ROCKETLANE_GET_ALL_CONVERSATIONS` | Get All Conversations | Tool to retrieve all conversations in Rocketlane. Use when you need to list, search, or filter conversations. Supports pagination and various filtering options including source ID, conversation name, and privacy status. |
| `ROCKETLANE_GET_ALL_FIELDS` | Get All Fields | Retrieve all custom fields available in the system. |
| `ROCKETLANE_GET_ALL_RESOURCE_ALLOCATIONS` | Get All Resource Allocations | Tool to retrieve all resource allocations from Rocketlane. Use when you need to get comprehensive allocation data for various projects within a specific date range. |
| `ROCKETLANE_GET_ALL_SPACES` | Get All Spaces | Tool to retrieve all spaces for a specific project in Rocketlane. Use when you need to list all spaces associated with a project, including space details like name, privacy status, and creation/update information. |
| `ROCKETLANE_GET_ALL_TASKS` | Get All Tasks | Tool to retrieve all tasks from Rocketlane with advanced filtering options. Supports filtering by project, status, dates, billable status, and more. Use this when you need to search or list tasks with specific criteria. |
| `ROCKETLANE_GET_ALL_TIMEOFFS` | Get All Time-Offs | Tool to retrieve all time-offs from Rocketlane with advanced filtering options. Use when you need to get comprehensive time-off data including leave entries, holidays, and absences. |
| `ROCKETLANE_GET_COMMENTS` | Get Comments | Tool to retrieve all comments from Rocketlane. Use when you need to fetch comments from tasks or project conversations with support for filtering, pagination, and sorting. |
| `ROCKETLANE_GET_COMPANY` | Get Company | This tool retrieves detailed information about a specific company/account in Rocketlane by its ID. It provides comprehensive information about the company including its status, address, currency, created date, updated date, custom fields, and other relevant metadata. |
| `ROCKETLANE_GET_CONVERSATION` | Get Conversation | Tool to retrieve detailed information about a conversation by its ID. Use when you need to get conversation details including name, description, members, and source information. |
| `ROCKETLANE_GET_FIELD_BY_ID` | Get Field By ID | Retrieve detailed information about a specific custom field using its unique identifier (fieldId). |
| `ROCKETLANE_GET_PHASE_BY_ID` | Get Phase by ID | Tool to retrieve extensive information about a specific phase by its unique identifier. Use when you need detailed phase data for project management operations. |
| `ROCKETLANE_GET_PROJECT_BY_ID` | Get Project by ID | Retrieves detailed information about a specific project using its unique identifier. |
| `ROCKETLANE_GET_SPACE` | Get Space by ID | Tool to retrieve detailed information about a specific space using its unique identifier. Use when you need to fetch space details including associated project, creation time, and privacy settings. |
| `ROCKETLANE_GET_TASK_BY_ID` | Get Task By Id | Retrieve extensive information about a specific task using the task's unique identifier (taskId). |
| `ROCKETLANE_GET_TEMPLATE_BY_ID` | Get Template By ID | Retrieve detailed information about a specific template using its unique identifier (templateId). NOTE: The exact API endpoint and response structure need to be verified from the official Rocketlane API documentation. |
| `ROCKETLANE_GET_TIME_ENTRIES` | Get Time Entries | Tool to retrieve all time entries from Rocketlane. It provides endpoints to get time entries with support for pagination, filtering by project ID, user ID, start and end dates. This allows tracking of time spent on various tasks, generating reports, and analyzing team productivity. |
| `ROCKETLANE_GET_TIME_ENTRY_BY_ID` | Get Time Entry By ID | Retrieve detailed information about a specific time entry using its unique identifier (timeEntryId). |
| `ROCKETLANE_GET_TIME_ENTRY_CATEGORIES` | Get Time Entry Categories | Tool to retrieve time entry categories from Rocketlane. Returns a paginated list of all available time entry categories. Use when you need to get the available categories for creating or filtering time entries. |
| `ROCKETLANE_GET_USER_BY_ID` | Get User By ID | Retrieve detailed information about a specific user using their unique identifier (userId). |
| `ROCKETLANE_LIST_COMPANIES` | List Companies | This tool retrieves a list of all companies/accounts in Rocketlane. It's a basic GET endpoint that returns all companies without requiring any specific resource IDs or additional parameters. The endpoint is independent and can be executed with just the authentication token. |
| `ROCKETLANE_LIST_CURRENCIES` | List Currencies | Returns a predefined list of commonly used currencies since Rocketlane API doesn't provide a dedicated currencies endpoint. This list includes major global currencies with their codes, names, and symbols. |
| `ROCKETLANE_LIST_PROJECT_PHASES` | List Project Phases | This tool retrieves a list of project phases from Rocketlane. It allows users to fetch and filter phases based on various parameters including projectID, startDate, dueDate, startDateActual, dueDateActual, phaseName, sortBy, sortOrder, limit, and pageToken. The API supports various operators for filtering such as .gt, .eq, .lt, .ge, .le, .cn, and .nc. Note: The API requires projectId to be specified, despite the official documentation listing it as optional. Calling the endpoint without projectId returns a 400 BAD_REQUEST error. This has been verified through direct API testing (see: https://developer.rocketlane.com/reference/get-all-phases). |
| `ROCKETLANE_LIST_PROJECTS` | List Projects | This tool retrieves a list of all projects in the Rocketlane instance. It provides project details including Project ID, Project Name, Project Status, Created Date, Owner Information, Customer Information, and other metadata. |
| `ROCKETLANE_LIST_TEMPLATES` | List Templates | This tool retrieves a list of all available templates in Rocketlane. It fetches all available templates in the account and returns a list of template objects containing details like template_id, name, description, created_at, updated_at, is_dynamic, and has_automations. |
| `ROCKETLANE_LIST_USERS` | List Users | This tool retrieves all users in the Rocketlane instance. It is an independent action that does not require any resource IDs or external dependencies. The endpoint returns detailed user information including user IDs, emails, names, roles, and statuses. |
| `ROCKETLANE_MOVE_TASK_TO_GIVEN_PHASE` | Move Task To Given Phase | Tool to move a task to a different phase by task ID and phase ID. Use when tasks need to be reorganized across different project phases. |
| `ROCKETLANE_REMOVE_ASSIGNEES_FROM_TASK` | Remove Assignees From Task | Tool to remove assignees from a task by its unique identifier. Use when you need to remove team members from a specific task. |
| `ROCKETLANE_REMOVE_DEPENDENCIES_FROM_TASK` | Remove Dependencies From Task | Tool to remove dependencies from a task by ID. Use when you need to unlink dependency relationships between tasks. |
| `ROCKETLANE_REMOVE_FOLLOWERS_FROM_TASK` | Remove Followers From Task | Tool to remove followers from a task by task ID. Use when you need to remove one or more followers from a specific task. |
| `ROCKETLANE_REMOVE_MEMBERS_FROM_CONVERSATION` | Remove Members from Conversation | Remove members from a conversation in Rocketlane. Use this when you need to remove team members or stakeholders from an existing conversation. |
| `ROCKETLANE_RETRIEVE_SUBSCRIPTION_DETAILS` | Retrieve Subscription Details | Retrieves detailed information about the current subscription. |
| `ROCKETLANE_SEARCH_INVOICES` | Search Invoices | Tool to retrieve all invoices from Rocketlane. Use when you need to get a list of all invoices accessible to the authenticated user. This endpoint returns invoice details including invoice numbers, dates, amounts, status, and associated customer and project information. |
| `ROCKETLANE_SEARCH_TIME_ENTRIES` | Search Time Entries | Tool to search time entries with filters in Rocketlane. Use when you need to find specific time entries based on criteria like date ranges, project, user, billable status, or duration. Supports advanced filtering using field.operator=value format (e.g., date.gt=2023-02-11, minutes.eq=250). |
| `ROCKETLANE_SEARCH_USER_BY_EMAIL` | Search User By Email | Search User By Email Id. |
| `ROCKETLANE_UPDATE_COMPANY` | Update Company | This tool updates an existing company/account in Rocketlane. It uses the PUT endpoint to update the company details identified by companyId. The action complements the existing create_company action and is essential for maintaining up-to-date company information, relying on Rocketlane's API specifications and company management endpoints. |
| `ROCKETLANE_UPDATE_CONVERSATION` | Update Conversation | Tool to update an existing conversation in Rocketlane by its ID. Use when you need to modify conversation details like name, description, or member inclusion settings. |
| `ROCKETLANE_UPDATE_FIELD` | Update Field | Tool to update field information by ID. Updates field properties including label, description, privacy settings, and enabled status. Use when you need to modify existing field metadata. |
| `ROCKETLANE_UPDATE_FIELD_OPTION` | Update Field Option | Tool to update an existing option's label and color in a SINGLE_CHOICE or MULTIPLE_CHOICE field. Use when modifying dropdown or select field option properties. |
| `ROCKETLANE_UPDATE_PHASE` | Update Phase | Tool to update phase information by phase ID. Use when you need to modify phase details such as name, dates, status, or privacy settings for an existing project phase. |
| `ROCKETLANE_UPDATE_PROJECT_BY_ID` | Update Project By Id | Updates an existing project's details using its unique identifier. |
| `ROCKETLANE_UPDATE_SPACE` | Update Space | Tool to update space details by its unique identifier. Use when you need to update space properties such as name or privacy settings. |
| `ROCKETLANE_UPDATE_SPACE_DOCUMENT` | Update Space Document | Tool to update a space document's properties by its unique identifier in Rocketlane. Use when you need to modify the name or URL of an existing space document. This action allows updating document metadata without recreating the document. |
| `ROCKETLANE_UPDATE_TASK_BY_ID` | Update Task by ID | Tool to update task details by ID. Use when you need to modify task information such as name, dates, status, progress, or custom fields. |
| `ROCKETLANE_UPDATE_TIME_ENTRY_BY_ID` | Update Time Entry by ID | Update existing time entry details using its unique identifier (timeEntryId). |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Rocketlane MCP server is an implementation of the Model Context Protocol that connects your AI agent to Rocketlane. It provides structured and secure access so your agent can perform Rocketlane operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before starting, make sure you have:
- Python 3.9 or higher
- A Composio account with an active API key
- Basic familiarity with Python and async programming

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

Install the required libraries.
What's happening:
- composio connects your agent to external SaaS tools like Rocketlane
- pydantic-ai lets you create structured AI agents with tool support
- python-dotenv loads your environment variables securely from a .env file
```bash
pip install composio pydantic-ai python-dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's happening:
- COMPOSIO_API_KEY authenticates your agent to Composio's API
- USER_ID associates your session with your account for secure tool access
- OPENAI_API_KEY to access OpenAI LLMs
```bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key
```

### 4. Import dependencies

What's happening:
- We load environment variables and import required modules
- Composio manages connections to Rocketlane
- MCPServerStreamableHTTP connects to the Rocketlane MCP server endpoint
- Agent from Pydantic AI lets you define and run the AI assistant
```python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
```

### 5. Create a Tool Router Session

What's happening:
- We're creating a Tool Router session that gives your agent access to Rocketlane tools
- The create method takes the user ID and specifies which toolkits should be available
- The returned session.mcp.url is the MCP server URL that your agent will use
```python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Rocketlane
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["rocketlane"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
```

### 6. Initialize the Pydantic AI Agent

What's happening:
- The MCP client connects to the Rocketlane endpoint
- The agent uses GPT-5 to interpret user commands and perform Rocketlane operations
- The instructions field defines the agent's role and behavior
```python
# Attach the MCP server to a Pydantic AI Agent
rocketlane_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[rocketlane_mcp],
    instructions=(
        "You are a Rocketlane assistant. Use Rocketlane tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
```

### 7. Build the chat interface

What's happening:
- The agent reads input from the terminal and streams its response
- Rocketlane API calls happen automatically under the hood
- The model keeps conversation history to maintain context across turns
```python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Rocketlane.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
```

### 8. Run the application

What's happening:
- The asyncio loop launches the agent and keeps it running until you exit
```python
if __name__ == "__main__":
    asyncio.run(main())
```

## Complete Code

```python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Rocketlane
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["rocketlane"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    rocketlane_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[rocketlane_mcp],
        instructions=(
            "You are a Rocketlane assistant. Use Rocketlane tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Rocketlane.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())
```

## Conclusion

You've built a Pydantic AI agent that can interact with Rocketlane through Composio's Tool Router. With this setup, your agent can perform real Rocketlane actions through natural language.
You can extend this further by:
- Adding other toolkits like Gmail, HubSpot, or Salesforce
- Building a web-based chat interface around this agent
- Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Rocketlane for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

## How to build Rocketlane MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/rocketlane/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/rocketlane/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/rocketlane/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/rocketlane/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/rocketlane/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/rocketlane/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/rocketlane/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/rocketlane/framework/cli)
- [Google ADK](https://composio.dev/toolkits/rocketlane/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/rocketlane/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/rocketlane/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/rocketlane/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/rocketlane/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/rocketlane/framework/crew-ai)

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Rocketlane MCP?

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

### Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic AI 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 Rocketlane tools.

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

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
