{
  "markdown": "# Parallel Task MCP\n\nThe **Parallel Task MCP** allows initiating deep research or task groups directly from your favorite LLM client. It can be a great way to get to know Parallel’s different APIs by exploring their capabilities, but can also be used as a way to easily do small experiments while developing production systems using Parallel APIs. Please read [our MCP docs here](https://docs.parallel.ai/integrations/mcp/getting-started) for more details.\n\n## Installation\n\nThe official installation instructions can be found [here](https://docs.parallel.ai/integrations/mcp/installation).\n\n```json\n{\n  \"mcpServers\": {\n    \"Parallel Task MCP\": {\n      \"url\": \"https://task-mcp.parallel.ai/mcp\"\n    }\n  }\n}\n```\n\n## Running locally\n\n<details><summary>Running locally</summary>\n\nThis repo contains a proxy to the mcp which is hosted at: https://task-mcp.parallel.ai/mcp\n\nHow to run and test locally:\n\n1. `wrangler dev`\n2. `npx @modelcontextprotocol/inspector`\n3. Connect to server: http://localhost:8787/mcp\n\n</details>\n",
  "bytes": 1018,
  "sha": "f1c0ca4222daf1bc258592653394ffc411329344c859b68cfbf2d2aa82c296df",
  "repo_slug": "parallel-web/task-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_parallel_task_mcp_3350402b/readme"
}