How to integrate Parallel Task MCP with Atomic Agent

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Parallel Task.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Parallel Task account. See the Atomic Agent documentation for installation instructions.

How Atomic Agent connects to Parallel Task

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect Parallel Task to Atomic Agent

1. Sign up or sign in to the Composio dashboard. Copy your API key.
2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
3. Ask Atomic Agent to do something in Parallel Task. It searches Composio for the right tool.
4. On first use, open the sign-in link returned in the chat. Connect your Parallel Task account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

The Parallel Task MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Parallel Task account. It provides structured and secure access to deep research and data enrichment tasks, so your agent can launch cited research, run batch enrichment, monitor progress, and retrieve finished results on your behalf.

• Deep research with citations: Have your agent research a single topic in depth and produce findings backed by citations.
• Batch data enrichment: Direct your agent to launch a group of enrichment tasks for multiple records at once.
• Task progress monitoring: Let the agent check whether a research or enrichment task is still running or has finished.
• Results in readable markdown: Instruct your agent to retrieve completed task results as markdown for easy reading and reuse.

Use Parallel Task from Atomic Agent

With your account connected, ask Atomic Agent to work with Parallel Task in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.