Browser Tools

contextfetch.dev

Provides web search, URL-to-Markdown extraction, similar-page discovery, and multi-query research evidence packs for LLM-ready web content.

1 endpoint13 known toolsFirst detected October 20, 2026Last detected October 20, 2026

ENDPOINT 1

https://api.contextfetch.dev/mcp

No auth detected

MCP server metadata

Name: contextfetch
Version: 1.0.1

Capabilities

tools

Server instructions

Web search and URL-to-Markdown with query-pruned context. Without a key: 25 calls/day per IP. With a key: send Authorization: Bearer cf_live_... When the free calls run out, contextfetch_get_free_key gets a free starter key.

Known tools 13

contextfetch_search

Search the web and get LLM-ready Markdown.

Inferred read-only

contextfetch_extract_url

Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved.

Inferred read-only

contextfetch_find_similar

Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain.

Inferred read-only

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).

Inferred read-only

contextfetch_deep_research

Same as contextfetch_research (kept for existing clients): up to 3 sub-queries run server-side, sources deduped and ranked against the question, one Markdown evidence pack with numbered sources and query-pruned passages.

Inferred read-only

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.

Inferred read-only

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).

Inferred read-only

contextfetch_map

List a website's URLs without fetching its pages: its sitemaps (from robots.

Inferred read-only

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.

Potential side effects

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.

Potential side effects

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.

Potential side effects

search

Search the web.

Inferred read-only

fetch

Fetch the full text of a search result by its id (a URL).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.contextfetch]
url = "https://api.contextfetch.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "contextfetch": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: contextfetch
Remote MCP URL: https://api.contextfetch.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "contextfetch": {
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "contextfetch": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "contextfetch",
  "transport": "streamable-http",
  "url": "https://api.contextfetch.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.