Skip to main content

What is MCP?

Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. With Parallel AI’s MCP server, your AI assistant can:
  • Find, import, and enrich leads
  • Browse and manage your AI agents
  • Create and monitor outreach sequences
  • Search your knowledge base documents
  • Generate AI content, images, audio, and video
  • Execute browser automation tasks
  • Access every platform feature via natural language

MCP Server URL

This server implements MCP Streamable HTTP Transport (JSON-RPC 2.0). It is compatible with mcp-remote and other standard MCP clients.

Available Tools

When a category has a skill (step-by-step instructions for a workflow), platform_list_capabilities names it under relatedSkills; assistants read it with the skills_getSkill action. For example, the Leads category links the lead-generation skill — see Leads via API & MCP.

Connecting Claude Desktop

1

Open your Claude Desktop config file

Locate the configuration file for your operating system:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
2

Add the MCP server

Paste the following into your config file, replacing your_api_key_here with your actual API key:
claude_desktop_config.json
3

Restart Claude Desktop

Fully quit and relaunch Claude Desktop so it picks up the new configuration.
4

Test the connection

Ask Claude something like:
  • “List my AI agents”
  • “Find 50 marketing directors at US SaaS companies with 51–200 employees and add them to a new list”
Claude will automatically use the Parallel AI tools to fulfill your request.

Connecting Cursor / Windsurf

1

Open the MCP settings

Navigate to Settings → MCP inside Cursor or Windsurf.
2

Add a new MCP server

Fill in the following details:
  • URL: https://api.parallellabs.app/api/v0/mcp
  • Authentication: Bearer token using your Parallel AI API key
3

Confirm the tools are available

The Parallel AI platform tools will appear in your AI assistant’s tool list. You can now reference them directly in your prompts.

Generic mcp-remote Connection

If you’re using any MCP client that supports mcp-remote, connect with a single command:

Authentication for MCP

MCP authentication follows the same pattern as the REST API. Company API Key:
Personal Access Key:
You can find your API keys on the Integrations page (Company API Keys) or your Profile page (Personal Access Keys) in the Parallel AI dashboard.

Example MCP Interactions

The tools work together to let your AI assistant discover and execute any platform action: find your company ID, browse a category, read an action’s parameters, then run it.
Every operation ID and its parameters are listed in the API reference. platform_get_action_details returns the same information for one operation.