Magnetic Integration for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Magnetic MCP or direct API to track projects, manage resources, update financials, and automate workflows through natural language.
Magnetic Logo
Gradient Top
Gradient Middle
Gradient Bottom
divider

Supported Tools

Tools
Get Current Follow-upsTool to retrieve upcoming follow-ups assigned to the authenticated user.
Search Client ContactsTool to search contacts by field or client id.
Get Contact TagsTool to get all tags associated with a contact.
Get Magnetic GroupingsTool to retrieve a list of groupings.
Get Grouping StatusesTool to retrieve the list of statuses for signed groupings.
Get Grouping TagsTool to retrieve tags associated with any groupings owned by the company.
Get Magnetic Opportunity StatusesTool to retrieve opportunity statuses.
Get Magnetic TaskTool to retrieve a task by its id.
Get Magnetic User by IDTool to get a magnetic user's details by id.
Get UsersTool to retrieve the list of all users in the authenticated user's company.
Get Grouping Custom Field DefinitionsTool to retrieve all custom field definitions for groupings.
Search Magnetic TasksTool to search tasks by a specified field and value.

Why Use Composio?

AI Native Magnetic Integration

  • Supports both Magnetic MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your Magnetic data

Managed Auth

  • Built-in API key handling—no more juggling sensitive credentials
  • Central place to manage, scope, and revoke Magnetic access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Magnetic
  • Scoped, least privilege access to Magnetic resources
  • Full audit trail of agent actions to support review and compliance

Connect Magnetic MCP Tool with your Agent

Python
TypeScript

Install Composio

python
pip install composio claude-agent-sdk
Install the Composio SDK and Claude Agent SDK

Create Tool Router Session

python
from composio import Composio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions

composio = Composio(api_key='your-composio-api-key')
session = composio.create(user_id='your-user-id')
url = session.mcp.url
Initialize the Composio client and create a Tool Router session

Connect to AI Agent

python
import asyncio

options = ClaudeAgentOptions(
    permission_mode='bypassPermissions',
    mcp_servers={
        'tool_router': {
            'type': 'http',
            'url': url,
            'headers': {
                'x-api-key': 'your-composio-api-key'
            }
        }
    },
    system_prompt='You are a helpful assistant with access to Magnetic tools.',
    max_turns=10
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query('List all current follow-ups assigned to me in Magnetic')
        async for message in client.receive_response():
            if hasattr(message, 'content'):
                for block in message.content:
                    if hasattr(block, 'text'):
                        print(block.text)

asyncio.run(main())
Use the MCP server with your AI agent

Connect Magnetic API Tool with your Agent

Python
TypeScript

Install Composio

python
pip install composio_openai
Install the Composio SDK

Initialize Composio and Create Tool Router Session

python
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
openai = OpenAI()
session = composio.create(user_id='your-user-id')
Import and initialize Composio client, then create a Tool Router session

Execute Magnetic Tools via Tool Router with Your Agent

python
tools = session.tools
response = openai.responses.create(
  model='gpt-4.1',
  tools=tools,
  input=[{
    'role': 'user',
    'content': 'Show this week\'s upcoming project follow-ups'
  }]
)
result = composio.provider.handle_tool_calls(
  response=response,
  user_id='your-user-id'
)
print(result)
Get tools from Tool Router session and execute Magnetic actions with your Agent

Use Magnetic with any AI Agent Framework

Choose a Framework you want to connect Magnetic with

OpenAI Agents SDK

OpenAI Agents SDK

Use Magnetic MCP with OpenAI Agents SDK

Claude Agents SDK

Claude Agents SDK

Use Magnetic MCP with Claude Agents SDK

Google ADK

Google ADK

Use Magnetic MCP with Google ADK

Langchain

Langchain

Use Magnetic MCP with Langchain

AI SDK

AI SDK

Use Magnetic MCP with AI SDK

Mastra AI

Mastra AI

Use Magnetic MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Magnetic MCP with LlamaIndex

CrewAI

CrewAI

Use Magnetic MCP with CrewAI

Pydantic AI

Pydantic AI

Use Magnetic MCP with Pydantic AI

Autogen

Autogen

Use Magnetic MCP with Autogen

Frequently Asked Questions

Do I need my own developer credentials to use Magnetic with Composio?

Yes, Magnetic requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

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.