# Parallel Task MCP server > Run deep web research and batch data enrichment jobs with Parallel and fetch the sourced results as Markdown. - Listing: https://mcp.tc/i/parallel-task - Connect: use the server's own URL `https://task-mcp.parallel.ai/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [Search & Web Data](https://mcp.tc/c/search-web) - Vendor: Parallel Web Systems - Homepage: - Repository: ## About Connects an assistant to the Parallel Task API. You can start a deep research job for a question that needs a detailed, sourced answer, or run enrichment over a list of inputs using a shared output schema. Jobs run asynchronously, so you check status and then retrieve the results as Markdown. Runs as a hosted streamable HTTP endpoint at https://task-mcp.parallel.ai/mcp. A Parallel account is required, and sign-in uses OAuth in the browser. Clients without OAuth support can send a Parallel API key as a Bearer token. Creating research or enrichment tasks is billable under Parallel's Task API pricing. ## What it can do - Start a deep research job for a question that needs cited sources - Enrich a list of inputs against a common output schema - Check whether a research run or task group is still active - Retrieve finished research or enrichment output as Markdown ## Example prompts - "Research Parallel Web Systems and write a company brief with sources." - "Enrich these three companies with website, headquarters and founding year." - "Check the status of my running research job." - "Get the Markdown result for my finished task group." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http parallel-task https://task-mcp.parallel.ai/mcp ``` 2. Start Claude Code, type `/mcp`, pick **parallel-task** and choose **Authenticate**. A browser window opens for the Parallel Web Systems sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Parallel Task** and paste this URL: ```url https://task-mcp.parallel.ai/mcp ``` 3. Click **Add**, then **Connect**, and sign in when Parallel Web Systems asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://task-mcp.parallel.ai/mcp` and click **Add**. 3. Click **Connect** and sign in when Parallel Web Systems asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://task-mcp.parallel.ai/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Parallel Web Systems to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "parallel-task": { "url": "https://task-mcp.parallel.ai/mcp" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"parallel-task","type":"http","url":"https://task-mcp.parallel.ai/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "parallel-task": { "type": "http", "url": "https://task-mcp.parallel.ai/mcp" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "parallel-task": { "serverUrl": "https://task-mcp.parallel.ai/mcp" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add parallel-task --url https://task-mcp.parallel.ai/mcp codex mcp login parallel-task ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.parallel-task] url = "https://task-mcp.parallel.ai/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http parallel-task https://task-mcp.parallel.ai/mcp ``` Then, inside Gemini CLI, run `/mcp auth parallel-task` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "parallel-task": { "type": "http", "url": "https://task-mcp.parallel.ai/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://task-mcp.parallel.ai/mcp`. ## Details - Server version: 1.0.0 - Last checked: 2026-10-03 (reachable, asks for credentials) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/parallel-task (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report