How to integrate Feathery MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Feathery Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Feathery to CrewAI using the Composio tool router. By the end, you'll have a working Feathery agent that can list all forms created this month, get schema for user registration form, fill document template with client details, show recent api connector errors for onboarding form through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Feathery account through Composio's Feathery 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 a Composio API key and configure your Feathery connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Feathery
  • Build a conversational loop where your agent can execute Feathery operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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

The Feathery MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Feathery account. It provides structured and secure access to your forms and workflow data, so your agent can perform actions like creating hidden fields, retrieving form schemas, listing documents, and managing account settings on your behalf.

  • Form discovery and management: Let your agent list all existing forms, retrieve specific form schemas, or permanently remove forms as needed.
  • Document automation and signing: Automatically fill or sign document templates and track generated document envelopes for streamlined data processing.
  • Hidden field configuration: Create new hidden fields or list all hidden fields within your forms for advanced workflow logic and data capture.
  • Account and team management: Fetch detailed account info, update user roles and permissions, and manage your Feathery team's access seamlessly.
  • Integration troubleshooting: List recent API connector errors tied to specific forms, making it easier to debug and maintain your integrations.

Supported Tools & Triggers

Tools
Edit Feathery AccountTool to edit an existing account’s role and permissions.
Get Account InfoTool to get your Feathery team name and list of accounts.
Fill or sign document templateTool to fill or sign a Feathery document template.
List Document EnvelopesTool to list generated document envelopes by document or user ID.
Create hidden fieldTool to create a new hidden field in a form.
Delete FormTool to delete an existing form.
Get form schemaTool to retrieve the schema of a specific form.
List FormsTool to list all forms in your Feathery account.
List Hidden FieldsTool to list all hidden form fields in the account.
List API Connector ErrorsTool to list recent API connector error logs for a form.
List Email IssuesTool to list email bounce and complaint events.
List Email LogsTool to list recently sent emails for a form.
List Quik Request LogsTool to list recent Quik integration request logs for a form.
Create or Fetch UserTool to create a new user or fetch an existing one.
Delete UserTool to delete a specific user by ID.
Get All User DataTool to retrieve all stored data fields for a user.
Get User SessionTool to get a user's form session and progress.
List UsersTool to list all users in your Feathery account.
Generate Workspace Login TokenTool to generate a login JWT for a workspace.

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

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Feathery connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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 crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Feathery via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Feathery MCP URL

Create a Composio Tool Router session for Feathery

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["feathery"],
)
url = session.mcp.url
What's happening:
  • You create a Feathery only session through Composio
  • Composio returns an MCP HTTP URL that exposes Feathery tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Feathery Assistant",
    goal="Help users interact with Feathery through natural language commands",
    backstory=(
        "You are an expert assistant with access to Feathery tools. "
        "You can perform various Feathery operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Feathery MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Feathery operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Feathery related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_feathery_agent.py

Complete Code

Here's the complete code to get you started with Feathery and CrewAI:

python
# file: crewai_feathery_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Feathery session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["feathery"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Feathery assistant agent
    toolkit_agent = Agent(
        role="Feathery Assistant",
        goal="Help users interact with Feathery through natural language commands",
        backstory=(
            "You are an expert assistant with access to Feathery tools. "
            "You can perform various Feathery operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Feathery operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Feathery related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Feathery through Composio's Tool Router. The agent can perform Feathery operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Feathery MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Feathery MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Feathery MCP with Claude Agent SDK

Google ADK

Google ADK

Use Feathery MCP with Google ADK

LangChain

LangChain

Use Feathery MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Feathery MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Feathery MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Feathery MCP with LlamaIndex

FAQ

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

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

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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 Feathery tools.

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

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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