Agents Index

ToolSnap MCP

Online

Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 47 tools.

Visit publisherConnectJSON

What it can do: 17 tools

  • tool_catalog read-onlyFree, read-only, no network. Browse all 47 tools in 10 families (web, seo, data, documents, images, media, utils, payments, recipes, meta). No args: families with id, label, one-liner, tool count. family='<id>': each too
  • use_toolFree wrapper. Runs any catalog tool missing from your tools/list exactly as a direct call: args pass through unchanged and the inner tool's price, payment, result and errors apply verbatim. Its hints are the worst case o
  • task_recipes read-onlyFree. Multi-tool workflow prompts (clone a site, SEO audit). No args → menu; recipe='<id>' → prompt.
  • memory_snippet read-onlyFree, read-only. Returns static text: a short note on when ToolSnap tools suit a task, plus how to store a note in your runtime's memory. This tool saves nothing. Use only if your user asks about persistent memory or Too
  • pricing read-onlyFree, read-only, no network, no arguments; calling it charges nothing. Call it before a paid tool to see its exact cost and whether first_call_free applies, or to choose pay-per-call vs prepaid. Returns a JSON menu: endp
  • fetch_extract read-onlyFree, read-only. Fetch a public http(s) URL and return its body as plain text: script, style, nav, header, footer and aside removed, tags stripped, entities decoded, whitespace collapsed. Median 98% fewer tokens than raw
  • fetch_html read-onlyFree, read-only. Fetch a page and return its HTML minus scripts, styles, svg, iframes, comments and inline handlers; tags and attributes stay, so structure is readable. For inspecting or rebuilding markup, not plain text
  • html_to_markdown read-onlyFree, read-only. Convert a fetched URL or an HTML string you pass (one of the two) to Markdown: headings, links, lists, emphasis, code, quotes. Drops nav, header, footer, aside, script and style. Returns text, cut at max
  • fetch_metadata read-onlyFree, read-only. Fetch a public http(s) URL and return its <head> metadata as JSON: url (after redirects), title, description, canonical, robots, author, keywords, lang, charset, og{} and twitter{} (prefix stripped), htt
  • pdf_text_extract read-onlyFree, read-only. Extract plain text from a PDF given as a URL (max 20 MB) or inline base64 (max 5 MB), one of the two. Returns text, cut at maxChars with a marker. Text-layer PDFs only: scans return little or nothing (no
  • csv_query read-onlyFree, read-only. Query a comma-separated CSV with a header row, from a URL (max 5 MB, streamed) or inline text, one of the two: select columns, filter rows, sort, limit. Returns {meta:{returned_rows,columns,total_rows,tr
  • json_query read-onlyFree, read-only. JSONPath-lite query on JSON from a URL or an inline string (one of the two). Returns matches as JSON: one match bare, several as an array. Supports $, .key, ['key'], [0], [-1], [*], ..key and [?(@.k op v
  • sitemap_parse read-onlyFree, read-only. Fetch one XML sitemap and return JSON. A urlset gives urls[] (loc, lastmod, changefreq, priority, plus image/news extensions), urlCount and truncated. A sitemap index gives type 'sitemapindex' and sitema
  • rss_parse read-onlyFree, read-only. Fetch an RSS 2.0 or Atom feed and return JSON: feed title, link, description, lastBuildDate, itemCount, truncated, and items[] with title, link, pubDate, guid, description (HTML stripped), author, catego
  • screenshot_urlScreenshot a page → public image URL. $0.04/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
  • keyword_research read-onlyGoogle Ads volume/CPC/competition for 1-20 keywords. $0.04 USDC/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
  • remove_backgroundRemove an image's background, return a transparent PNG URL. $0.03 USDC/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure

Connect it

Claude Code
claude mcp add --transport http toolsnap-mcp https://mcp.toolsnap.app/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.toolsnap.app/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "toolsnap-mcp": {
      "url": "https://mcp.toolsnap.app/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "toolsnap-mcp": {
      "type": "http",
      "url": "https://mcp.toolsnap.app/mcp"
    }
  }
}

Questions

What does ToolSnap MCP do?

Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 47 tools. It exposes 17 tools to AI assistants.

What tools does ToolSnap MCP provide?

17 tools, including tool_catalog, use_tool, task_recipes, memory_snippet, pricing, fetch_extract, fetch_html, html_to_markdown, fetch_metadata, pdf_text_extract, csv_query, json_query….

How do I connect ToolSnap MCP to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.toolsnap.app/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does ToolSnap MCP require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is ToolSnap MCP online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes ToolSnap MCP?

toolsnap.app. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Web Search & Scraping