
Parallel Task MCP
This connects Claude to Parallel's research and task orchestration APIs, letting you kick off deep research tasks or coordinate task groups without leaving your chat. It's hosted as a remote server, so there's no local setup beyond adding the URL to your MCP config. The main use case is exploring what Parallel's APIs can do before you build production integrations, though it works fine for quick experiments too. If you're already using Parallel for AI workflows and want faster iteration cycles, this gives you a conversational interface to their task system. The repo includes a local proxy setup if you want to poke around the implementation or test changes before they hit the hosted endpoint.
- GitHub stars
- 12
- tools
- 4
- transport
- HTTP
- last updated
- Jan 9, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
createDeepResearchStarts a research job for a question that needs a detailed, sourced answer.
Starts a research job for a question that needs a detailed, sourced answer.
No parameter schema in public metadata yet.
createTaskGroupStarts enrichment jobs for a list of inputs using a common output schema.
Starts enrichment jobs for a list of inputs using a common output schema.
No parameter schema in public metadata yet.
getStatusChecks whether a run or group is still active.
Checks whether a run or group is still active.
No parameter schema in public metadata yet.
getResultMarkdownRetrieves research or enrichment output as Markdown.
Retrieves research or enrichment output as Markdown.
No parameter schema in public metadata yet.
Sponsors
Readme
Parallel Task MCP
Deep research and data enrichment from your AI assistant.
Research a question or enrich a small dataset, then retrieve the results without leaving your agent. Parallel hosts the service; you do not need to run this repository to use it.
Task MCP requires a Parallel account and authentication. Unlike the free Search MCP, creating research or enrichment tasks is billable. Review Task API pricing before starting work.
Setup documentation · Get an API key · Task MCP documentation
Manual setup
Choose one connection method for your client. Reuse an existing connection to this endpoint rather than adding it twice.
Claude Code
Run this in the project where you want to use Parallel:
claude mcp add --transport http --scope project parallel-task https://task-mcp.parallel.ai/mcp
Details
- Repository
- github.com/parallel-web/task-mcp
- Website
- parallel.ai
- Category
- Productivity & Office
- Transport
- HTTP
- Registry
- MCP registry, active