Labsco
MCP SERVER · OFFICIAL PROJECT

Parallel Web Search

by Parallel

Two tools — search and fetch — usable with no key, plus a separate authenticated endpoint for deep research.

Web Search EnginesVerified
Summary
Both tools take an objective, not just a query — which is what makes the excerpts worth reading.

Passing what you are trying to find out, alongside the search terms, lets the server select excerpts against the goal rather than against keyword overlap. That is the difference between a snippet that happens to contain the word and one that answers the question. Splitting fast search from authenticated deep research is the other sensible division: the cheap path stays open and anonymous.

What it is

Parallel publishes two endpoints. The search one answered our probe unauthenticated with two tools; a separate Task endpoint handles deep research and enrichment and always needs credentials.

What you get
  • web_search — low-latency search returning LLM-friendly results with excerpts, guided by a stated objective
  • web_fetch — extract content from specific URLs, documented as a follow-up for when search excerpts are not enough
  • On the Task endpoint: createDeepResearch, createTaskGroup, getStatus, getResultMarkdown
Requirements

Nothing for search. The Task endpoint needs an API key or OAuth. One-click install links exist for Cursor, VS Code, LM Studio and Goose.

Setup effort

One command — npx -y mcp-remote https://search.parallel.ai/mcp