SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Parma MCP with Mastra AI

Connect Mastra AI to Parma MCP. Show your parma crm user profile details, list all dataset ids in parma ckan, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
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 Mastra AI using the Composio tool router. By the end, you'll have a working Parma agent that can manage relationships and groups, add and update notes, track deals and pipeline stages, and list users through natural language commands.

This guide will help you understand how to give your Mastra AI 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.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Parma with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKLlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Parma tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Parma tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Parma agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

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:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Parma through MCP.
3

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_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 your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models
5

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session
6

Create a Tool Router session for Parma

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["parma"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Parma MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "parma" for Parma access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to
7

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Parma toolkit
8

Create the Mastra agent

typescript
const agent = new Agent({
    name: "parma-mastra-agent",
    instructions: "You are an AI agent with Parma tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM
9

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

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

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        parma: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Parma toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

Here's the complete code to get you started with Parma and Mastra AI:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["parma"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      parma: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "parma-mastra-agent",
    instructions: "You are an AI agent with Parma tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { parma: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Parma through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows
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

Retrieve dataset metadata from Parma’s open data portal data.

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

List deals in the Parma account, optionally selecting a page.

List Groups

List groups in the Parma account, optionally filtered by a search query and selected by page.

List Notes

List notes in the Parma account, optionally selecting a page.

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

List notes linked to a specific relationship, optionally selecting a page.

List Relationships

List relationships in the Parma account, with optional filters such as name, type, or contact details.

List Stages

Tool to retrieve all stages in the Parma account.

List Users

List users in the Parma account, including their IDs, names, and email addresses.

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.

FRAMEWORKS

How to build Parma MCP Agent with another framework

Claude Code logo

Claude Code

Use Parma MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Parma MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Parma MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Parma MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Parma MCP with Grok Bot

Codex logo

Codex

Use Parma MCP with Codex

OpenClaw logo

OpenClaw

Use Parma MCP with OpenClaw

Hermes logo

Hermes

Use Parma MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Parma MCP with Atomic Agent

Google ADK logo

Google ADK

Use Parma MCP with Google ADK

LangChain logo

LangChain

Use Parma MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Parma MCP with Vercel AI SDK

LlamaIndex logo

LlamaIndex

Use Parma MCP with LlamaIndex

CrewAI logo

CrewAI

Use Parma MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Parma MCP with Pydantic AI

AutoGen logo

AutoGen

Use Parma MCP with AutoGen

FAQ

Frequently asked questions

Start with Parma.It takes 30 seconds.

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

Start building