Parallel Search MCP server

Tools provided by Parallel Search 2

Some details were sanitized for public display.

• web_fetchoutputSchema declared

  Purpose: Fetch and extract relevant content from specific web URLs. Use only when web_search excerpts are insufficient for the task at hand. Ideal Use Cases: - The user asked about a specific URL or page - You need exact wording or quotes that excerpts may have truncated - You need full-page analysis (long article, document, or page structure) - web_search excerpts are conflicting or clearly insufficient to answer For multiple independent extraction objectives, make separate web_fetch calls concurrently. Put related URLs that share one objective in a single call.

  Input allow_live_fetch?: boolean, full_content?: boolean, model_name?: string, objective?: any, search_queries?: any, session_id?: string, urls: array

  • allow_live_fetch?: booleanoptional

    Whether live fetching is allowed. Leave true for the freshest available content. Set false to use cached content only, which makes web_fetch much faster by avoiding the source website, but may return older content.

  • full_content?: booleanoptional

    Prefer leaving this off. The default excerpt mode returns LLM-optimized snippets focused on your objective — they are much smaller, cheaper, and usually all you need. Only set to true when you explicitly need the entire page as markdown (e.g. reading a long article in full, or running a document through a downstream summarizer). Warning: enabling full content can return a large amount of content — often tens of thousands of tokens for a long article. This may exceed your MCP client's tool-output limit and will substantially increase response size and latency.

  • model_name?: stringoptional

    The identifier of the LLM model making this tool call (e.g. 'claude-opus-4.7', 'gpt-5.5', 'gemini-2.5-pro'). Before the first call, verify the exact active model slug from trusted runtime/session metadata or active client configuration. Pass the full slug verbatim; never shorten or substitute a model-family alias like 'gpt-5'. Used for product analytics only; does not affect search behavior.

  • objective?: anyoptional

    Natural-language description of what information you're looking for from the URLs. Limit to 200 characters.

  • search_queries?: anyoptional

    Optional keyword search queries (3-6 words each) used together with objective to focus excerpts on the most relevant content. Pass the queries from the prior web_search call that surfaced these URLs, if applicable.

  • session_id?: stringoptional

    Stable identifier for the current conversation. Generate a random value (UUID or 32+ character hex string) at the start of your session and reuse the exact same value on every web_search / web_fetch call. Do NOT change it between turns. Used for free-tier rate limiting and correlating your tool calls in our logs; ignored on paid-tier keys.

  • urls: arrayrequired

    List of URLs to extract content from. Must be valid HTTP/HTTPS URLs. Up to 20 URLs per request.

• web_searchoutputSchema declared

  Purpose: Perform web searches and return LLM-friendly results, including excerpts that are usually sufficient to answer directly without a follow-up fetch. Ideal Use Cases: - Answering questions that require fresh or current information - Research, comparison, documentation, and troubleshooting questions - Broad tasks where multiple `search_queries` can be issued in a single call For multiple independent objectives, make one web_search call per objective concurrently. Put related query variations for the same objective in a single call's search_queries list.

  Input model_name?: string, objective: string, search_queries: array, session_id?: string

  • model_name?: stringoptional

    The identifier of the LLM model making this tool call (e.g. 'claude-opus-4.7', 'gpt-5.5', 'gemini-2.5-pro'). Before the first call, verify the exact active model slug from trusted runtime/session metadata or active client configuration. Pass the full slug verbatim; never shorten or substitute a model-family alias like 'gpt-5'. Used for product analytics only; does not affect search behavior.

  • objective: stringrequired

    Natural-language description of what the web search is trying to find. Try to make the search objective atomic, looking for a specific piece of information. May include guidance about preferred sources or freshness.

  • search_queries: arrayrequired

    Concise keyword search queries, 3-6 words each. They may use site: with a bare domain (such as site:example.com), but never a URL path after the domain and never quoted phrases. At least one query is required; provide 2-3 for best results. For broad tasks, you can include multiple related queries in a single call instead of chaining web_search calls. The queries should be related to the objective.

  • session_id?: stringoptional

    Stable identifier for the current conversation. Generate a random value (UUID or 32+ character hex string) at the start of your session and reuse the exact same value on every web_search / web_fetch call. Do NOT change it between turns. Used for free-tier rate limiting and correlating your tool calls in our logs; ignored on paid-tier keys.