How to integrate Hjarni MCP with OpenAI Agents SDK

This guide walks you through connecting Hjarni to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Hjarni agent that can create notes, read your notes, list containers, manage tags, and restore trashed notes through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Hjarni account through Composio's Hjarni MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Hjarni logoHjarni
Api Key

Hjarni is a personal knowledge management platform for notes, containers, tags, and linked ideas. It helps you keep knowledge organized, searchable, and easier to maintain.

15 Tools

Introduction

This guide walks you through connecting Hjarni to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Hjarni agent that can create notes, read your notes, list containers, manage tags, and restore trashed notes through natural language commands.

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

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

Also integrate Hjarni 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 Hjarni
  • Configure an AI agent that can use Hjarni as a tool
  • Run a live chat session where you can ask the agent to perform Hjarni 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 Hjarni MCP server, and what's possible with it?

The Hjarni MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hjarni account. It provides structured and secure access to your notes, containers, and tags, so your agent can create, find, organize, update, and recover knowledge on your behalf.

  • Note creation and editing: Have your agent create one or many Markdown notes, update their content and metadata, and place them in your inbox or chosen containers.
  • Knowledge search and review: Instruct your agent to list and filter active, archived, favorited, or inbox notes, then retrieve a note with its content, tags, attachments, and links.
  • Container organization: Let the agent create root or nested containers and update their names, descriptions, placement, ordering, or AI instructions.
  • Tag management: Direct your agent to create and rename tags, list available tags, and review how many notes use each one.
  • Trash and account oversight: Have your agent move notes to recoverable Trash, review trashed notes and purge dates, restore notes, or check account usage and quotas.

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 Hjarni 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 Hjarni.
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 Hjarni
const session = await composio.create(userId as string, {
  toolkits: ['hjarni'],
});
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 hjarni.
  • The router checks the user's Hjarni connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Hjarni.
  • This approach keeps things lightweight and lets the agent request Hjarni 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 Hjarni. Help users perform Hjarni 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 Hjarni 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 Hjarni 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 Hjarni.
  • 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 Hjarni 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: ['hjarni'],
  });
  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 Hjarni. Help users perform Hjarni 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 Hjarni MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Hjarni.

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 Hjarni action and event your agent gets out of the box.

Create Container

Create a root or nested Hjarni container for organizing notes.

Create Note

Create a Markdown note in the inbox or a container.

Create Notes

Create 1-25 Markdown notes in order and return one result per input.

Create Tag

Create a Hjarni tag for organizing notes.

Get Account Status

Return the connected Hjarni identity, token scope, plan, teams, and current resource usage and quotas.

Get Note

Get one Hjarni note by ID with its Markdown body, tags, container, attachments, links, and optimistic-lock version.

List Containers

List Hjarni containers as active roots, archived roots, or all active containers in a flat view.

List Notes

List and filter personal Hjarni notes, including active, inbox, archived, or favorited notes.

List Tags

List all Hjarni tags and their note counts.

List Trashed Notes

List recoverable trashed Hjarni notes with their deletion and scheduled purge times.

Rename Tag

Rename an existing Hjarni tag without changing its note associations.

Restore Note

Restore a note from Trash before its scheduled purge and return the active note.

Move Note to Trash

Move a note to recoverable Trash.

Update Container

Update a Hjarni container's name, description, parent, position, or container-specific AI instructions.

Update Note

Update note metadata, placement, tags, or body.

FAQ

Frequently asked questions

With a standalone Hjarni MCP server, the agents and LLMs can only access a fixed set of Hjarni tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Hjarni 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 Hjarni tools.

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

Start with Hjarni.It takes 30 seconds.

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

Start building