# Parallel Task MCP server

> Starts deep research jobs and dataset enrichment tasks and retrieves their results as Markdown without leaving the agent.

- Repository: https://github.com/parallel-web/task-mcp
- Page: https://hostedmcp.org/servers/parallel-web/task-mcp
- Transport: remote
- Stars: 16
- Latest version: 1.0.0

## Install

### Claude Code

```sh
claude mcp add --transport http task-mcp https://task-mcp.parallel.ai/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "task-mcp": {
      "url": "https://task-mcp.parallel.ai/mcp"
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "task-mcp": {
      "type": "http",
      "url": "https://task-mcp.parallel.ai/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"task-mcp","type":"http","url":"https://task-mcp.parallel.ai/mcp"}'
```

### Codex

```sh
codex mcp add task-mcp --url https://task-mcp.parallel.ai/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.task-mcp]
url = "https://task-mcp.parallel.ai/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http task-mcp https://task-mcp.parallel.ai/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "task-mcp": {
      "url": "https://task-mcp.parallel.ai/mcp",
      "type": "http"
    }
  }
}
```

## FAQ

### What tools does the Parallel Task MCP server provide?

It provides four tools: createDeepResearch, createTaskGroup, getStatus, and getResultMarkdown.

### How do I check progress on a research job?

Keep the run or group ID from when you started the job, then call getStatus to check progress while continuing other work.

### Do I need a Parallel account to use Task MCP?

Yes, it requires a Parallel account and authentication, and starting research or enrichment jobs is billable.

### How do I authenticate the Parallel Task MCP server?

You can complete a browser sign-in via OAuth, or use a Parallel API key as a Bearer token in the Authorization header.
