contextfetch_answer

Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended question. Costs 1 credit.

read-only

Argument	Type	Description
query*	string	The question.
num_results	integer	Pages searched for passages (1-10, default 5).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "The question."
    },
    "num_results": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1,
      "description": "Pages searched for passages (1-10, default 5)."
    }
  }
}

contextfetch_auto_reload

Turn auto-reload on or off, or change it: when credits drop below `threshold`, the saved card buys `pack` again, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap cannot be raised above $500 here.

Argument	Type	Description
pack	string	Pack to buy: instant $15/15,000, builder $50/60,000, scale $150/200,000.
enabled*	boolean	true to turn auto-reload on, false to turn it off.
threshold	integer	Reload when credits drop below this (100-100,000, default 1,000).
monthly_max_usd	number	Monthly spending cap in USD (at most 500).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "enabled"
  ],
  "properties": {
    "pack": {
      "enum": [
        "instant",
        "builder",
        "scale"
      ],
      "type": "string",
      "description": "Pack to buy: instant $15/15,000, builder $50/60,000, scale $150/200,000."
    },
    "enabled": {
      "type": "boolean",
      "description": "true to turn auto-reload on, false to turn it off."
    },
    "threshold": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 100,
      "description": "Reload when credits drop below this (100-100,000, default 1,000)."
    },
    "monthly_max_usd": {
      "type": "number",
      "maximum": 500,
      "description": "Monthly spending cap in USD (at most 500).",
      "exclusiveMinimum": 0
    }
  }
}

contextfetch_balance

Show the API key's remaining credits, daily burn rate (7-day average) and auto-reload settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

contextfetch_crawl

Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50). Pass `query` to rank the pages by relevance and return only their relevant passages. Costs 1 credit per page returned.

read-only

Argument	Type	Description
url*	string	Public http(s) start URL.
limit	integer	Maximum pages to return (1-50, default 10).
query	string	Optional topic: ranks pages and prunes each to the relevant passages.
max_depth	integer	Link hops from the start page (0-3, default 1).
exclude_paths	array	Regexes; never follow links whose path matches one.
include_paths	array	Regexes; only follow links whose path matches one, e.g. ["^/docs/"].

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) start URL."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum pages to return (1-50, default 10)."
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Optional topic: ranks pages and prunes each to the relevant passages."
    },
    "max_depth": {
      "type": "integer",
      "default": 1,
      "maximum": 3,
      "minimum": 0,
      "description": "Link hops from the start page (0-3, default 1)."
    },
    "exclude_paths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "description": "Regexes; never follow links whose path matches one."
    },
    "include_paths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "description": "Regexes; only follow links whose path matches one, e.g. [\"^/docs/\"]."
    }
  }
}

contextfetch_deep_research

Deep research in one call, no LLM: a deep search of the question, its sub-topics (or your sub_queries) as searches of their own, and the pages its list and index results link to, returned as one cited report: summary, key facts, a section per sub-topic and the sources, every passage quoted verbatim with [n]. Costs 1 credit. For a quick evidence pack use contextfetch_research.

read-only

Argument	Type	Description
query*	string	The research question.
sub_queries	array	Up to 3 search queries covering different angles of the question. Strongly recommended.
num_results_per_query	integer	Results per sub-query (1-25, default 5; at most 10 are used).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "The research question."
    },
    "sub_queries": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 3,
      "minItems": 1,
      "description": "Up to 3 search queries covering different angles of the question. Strongly recommended."
    },
    "num_results_per_query": {
      "type": "integer",
      "default": 5,
      "maximum": 25,
      "minimum": 1,
      "description": "Results per sub-query (1-25, default 5; at most 10 are used)."
    }
  }
}

contextfetch_extract_url

Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass `query` to get only the passages relevant to it instead of the whole page.

read-only

Argument	Type	Description
url*	string	Public http(s) URL to read.
query	string	Optional question or topic; returns only the relevant passages.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) URL to read."
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Optional question or topic; returns only the relevant passages."
    }
  }
}

contextfetch_find_similar

Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.

read-only

Argument	Type	Description
url*	string	Public http(s) URL to find similar pages for.
num_results	integer	Number of results to return (1-25, default 5).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) URL to find similar pages for."
    },
    "num_results": {
      "type": "integer",
      "default": 5,
      "maximum": 25,
      "minimum": 1,
      "description": "Number of results to return (1-25, default 5)."
    }
  }
}

contextfetch_get_free_key

Get a free ContextFetch API key (no signup, no payment) with starter credits, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <key>`.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

contextfetch_map

List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs 1 credit.

read-only

Argument	Type	Description
url*	string	Public http(s) URL of the site (any page on it).
limit	integer	Maximum URLs (1-5,000, default 100).
exclude_paths	array	Regexes; never list URLs whose path matches one.
include_paths	array	Regexes; only list URLs whose path matches one, e.g. ["^/blog/"].

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public http(s) URL of the site (any page on it)."
    },
    "limit": {
      "type": "integer",
      "default": 100,
      "maximum": 5000,
      "minimum": 1,
      "description": "Maximum URLs (1-5,000, default 100)."
    },
    "exclude_paths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "description": "Regexes; never list URLs whose path matches one."
    },
    "include_paths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "description": "Regexes; only list URLs whose path matches one, e.g. [\"^/blog/\"]."
    }
  }
}

contextfetch_research

Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim (no generated text). Costs 1 credit. Pass your own `sub_queries` (distinct angles on the question) for better coverage; if omitted they are derived from `query`: the query, query + "documentation", and query + "benchmark" (speed or comparison questions) or + "example".

read-only

Argument	Type	Description
query*	string	The research question.
sub_queries	array	Up to 5 search queries covering different angles of the question. Recommended.
num_results_per_query	integer	Results per sub-query (1-10, default 5).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "The research question."
    },
    "sub_queries": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 5,
      "minItems": 1,
      "description": "Up to 5 search queries covering different angles of the question. Recommended."
    },
    "num_results_per_query": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1,
      "description": "Results per sub-query (1-10, default 5)."
    }
  }
}

contextfetch_search

Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.

read-only

Argument	Type	Description
query*	string	Natural-language search query.
topic	string	news: news sources, recent pages first. finance: SEC filings and finance sites. Default general.
country	string	Two-letter country code (US, DE): that country's results rank higher.
category	string	Focus on one kind of page: company, research paper, news, pdf, github, personal site, linkedin profile, financial report, people.
language	string	Two-letter language code (en, de): results in that language rank higher.
time_range	string	Only pages published in the last day, week, month or year.
num_results	integer	Number of results to return (1-25, default 5).
exclude_domains

fetch

Fetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.

read-only

Argument	Type	Description
id*	string	An id from `search` (the page URL).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "An id from `search` (the page URL)."
    }
  }
}

search

Search the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.

read-only

Argument	Type	Description
query*	string	Search query.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Search query."
    }
  }
}

ContextFetch

Try it

contextfetch_answer

ContextFetch

Try it

contextfetch_answer

Tools (13)