How to integrate Parma MCP with OpenAI Agents SDK

This guide walks you through connecting Parma to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Parma agent that can show your parma crm user profile details, list all dataset ids in parma ckan, fetch full metadata for all parma datasets through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Parma account through Composio's Parma MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Parma logoParma
Oauth2Api Key

Parma CRM is a relationship management app designed to help you accelerate growth by deepening and nurturing your business relationships. It streamlines your networking, contact tracking, and follow-ups in one place.

23 Tools

Introduction

This guide walks you through connecting Parma to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Parma agent that can show your parma crm user profile details, list all dataset ids in parma ckan, fetch full metadata for all parma datasets through natural language commands.

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

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

Also integrate Parma with

TL;DR

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

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Parma MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, and more directly to your Parma CRM account. It provides structured and secure access to your CRM data, so your agent can retrieve user profiles, access dataset catalogs, and manage critical business information on your behalf.

  • Comprehensive dataset catalog access: Instantly retrieve dcat-us 1.1 compliant metadata for all datasets in your Parma open data portal, making it easy to audit or analyze your entire data catalog.
  • Personalized user profile retrieval: Ask your agent to fetch the authenticated user's profile details, helping you quickly access account info or tailor interactions for specific users.
  • Efficient dataset identification: Let your agent list all dataset identifiers from Parma's CKAN instance, streamlining workflows that depend on knowing what's available in your data ecosystem.
  • Data-driven relationship management: Empower your agent to surface, summarize, or cross-reference CRM datasets, deepening insights into your business relationships and opportunities.

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

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Parma project
  • Some knowledge of Python or Typescript
2

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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Parma.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Parma
const session = await composio.create(userId as string, {
  toolkits: ['parma'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only parma.
  • The router checks the user's Parma connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Parma.
  • This approach keeps things lightweight and lets the agent request Parma tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Parma. Help users perform Parma operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Parma and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Parma operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Parma.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Parma and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['parma'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Parma. Help users perform Parma operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Parma MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Parma.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

Every Parma action and event your agent gets out of the box.

Add Relationship to Group

Tool to add a relationship to a group in Parma.

Create Note

Tool to create a new note in the Parma account.

Create Relationship

Tool to create a new relationship in Parma.

Get data.json metadata

Tool to retrieve DCAT-US 1.

Delete Relationship

Tool to delete a relationship from Parma by its ID.

Get Pipeline

Tool to retrieve a pipeline by its ID.

Get Relationship

Tool to retrieve a relationship by its unique ID.

Get Stage

Tool to retrieve a stage by its unique identifier.

Get User by ID

Tool to retrieve a user by their unique ID.

Get User Profile

Tool to retrieve the authenticated user's profile.

List Deals

Tool to retrieve all deals from the Parma account.

List Groups

Tool to retrieve all groups in the Parma account.

List Notes

Tool to retrieve all notes from the Parma account.

List Pipelines

Tool to list all pipelines in the Parma account.

List Relationship Groups

Tool to retrieve all groups linked to a specific relationship.

List Relationship Notes

Tool to list all notes linked to a relationship.

List Relationships

Tool to list all relationships in the Parma account.

List Stages

Tool to retrieve all stages in the Parma account.

List Users

Tool to list all users in the Parma account.

List Parma CKAN datasets

Tool to retrieve all dataset identifiers from the Parma CKAN instance.

Remove Relationship From Group

Tool to remove a relationship from a group.

Update Note

Tool to update an existing note in the Parma account.

Update Relationship

Tool to update an existing relationship in the Parma account.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents 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 Parma tools.

Yes, absolutely. You can configure which Parma 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.

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 Parma data and credentials are handled as safely as possible.

Start with Parma.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Parma tool your agent needs.Free to start.

Start building