ToolSnap MCP

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

Should I use this

Description quality

99%

Schema completeness

92%

Naming quality

85%

Poisoning risk

100%

Permission match

100%

Protocol compliance

100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~3,540Tokens (tool definitions)

~1.0 KBTypical response size

Significant attention impact (2.77% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "toolsnap-mcp": {
      "url": "https://mcp.toolsnap.app/mcp"
    }
  }
}

Remote endpoints

https://mcp.toolsnap.app/mcpstreamable-http

What it can do

Tool inventory

Free, 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 tool with name, price, description, notes, inputSchema. tool='<name>': that entry alone; wins over family. Unknown ids error naming the valid families. Run what you find via use_tool.

Input Schema

{
  "type": "object",
  "properties": {
    "family": {
      "type": "string",
      "description": "Family id, e.g. 'web', 'data'. Lists its tools with schemas."
    },
    "tool": {
      "type": "string",
      "description": "Exact tool name, e.g. 'fetch_rendered'. Takes precedence over family."
    }
  },
  "required": []
}

Free 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 over the whole catalog: not read-only because some inner tools create a render, a stored file or a ledger entry; never destructive because no catalog tool deletes or overwrites anything. Get the inner tool's name, schema and its own annotations from tool_catalog(tool='<name>') first. A missing or unknown name errors pointing to tool_catalog; it cannot call itself.

Input Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Exact tool name from tool_catalog. Not 'use_tool'."
    },
    "args": {
      "type": "object",
      "description": "Object matching that tool's inputSchema. Omit if none required."
    }
  },
  "required": [
    "name"
  ]
}

Free. Multi-tool workflow prompts (clone a site, SEO audit). No args → menu; recipe='<id>' → prompt.

Input Schema

{
  "type": "object",
  "properties": {
    "recipe": {
      "type": "string",
      "description": "Recipe id; omit for menu."
    }
  },
  "required": []
}

Free, 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 ToolSnap setup; show them the text and save it only with their approval.

Input Schema

{
  "type": "object",
  "properties": {
    "harness": {
      "type": "string",
      "enum": [
        "claude-code",
        "claude-desktop",
        "hermes",
        "grok-build",
        "openclaw",
        "generic"
      ],
      "description": "Your agent runtime, to tailor the save instruction. Omit for a generic one."
    }
  },
  "required": []
}

Free, 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: endpoint and docs URLs; payment with x402 USDC on Base, minimum deposit, prepaid discount and SpendAuthorization fields; tools[] with name and tier free|paid, plus price_usdc, prepaid_price_usdc, first_call_free and a value note for paid ones. Flat prices are exact; fal.ai media tools show a default-args quote. For what a tool does and its schema use tool_catalog; this one is only about cost.

Input Schema

{
  "type": "object",
  "properties": {},
  "required": []
}

Free, 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 HTML. Follows up to 5 redirects, 10 s timeout; private and local hosts are rejected and non-2xx responses error with the HTTP status. Text past maxChars is cut and ends with '[Truncated at N chars]': raise maxChars (max 32000) or use fetch_html for everything. Runs no JavaScript: a client-side-rendered SPA or a bot/login wall yields almost no text, so the call errors instead of returning an empty shell and names the fix (fetch_rendered, paid, runs a browser; screenshot_url; or headers for auth). For title/OG/JSON-LD only use fetch_metadata; for Markdown with links use html_to_markdown.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public http:// or https:// URL. Local and private hosts are rejected."
    },
    "maxChars": {
      "type": "number",
      "description": "Characters of text to return. Default 8000, max 32000 (higher values are clamped). Truncated output ends with a '[Truncated at N chars]' marker."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward for pages behind login: Authorization, Cookie, X-API-Key only. Dropped if a redirect leaves the original host."
    }
  },
  "required": [
    "url"
  ]
}

Free, 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 (fetch_extract gives that). Runs no JavaScript: SPAs return an empty shell. Cut at maxChars with a marker.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "http(s) page URL. Private addresses are refused."
    },
    "maxChars": {
      "type": "number",
      "description": "Output cap, chars. Default 16000, max 64000."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward (Authorization, Cookie…)."
    }
  },
  "required": [
    "url"
  ]
}

Free, 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 maxChars with a marker. Runs no JavaScript: SPAs return an empty shell. Tables become plain text.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Page URL to fetch. Not with html."
    },
    "html": {
      "type": "string",
      "description": "HTML text to convert. Not with url."
    },
    "maxChars": {
      "type": "number",
      "description": "Output cap, chars. Default 12000, max 50000."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward (Authorization, Cookie…)."
    }
  }
}

Free, 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), httpEquiv{}, jsonLd[] (parsed blocks, malformed ones skipped). Absent fields are null or {}. Reads only the first 512 KB, follows up to 5 redirects, 10 s timeout; private and local hosts are rejected and non-2xx responses error with the HTTP status. Runs no JavaScript, so tags injected client-side are not seen. Not for body text: use fetch_extract (plain text) or fetch_html (raw HTML).

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public http:// or https:// URL. Local and private hosts are rejected."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward for pages behind login: Authorization, Cookie, X-API-Key only. Dropped if a redirect leaves the original host."
    }
  },
  "required": [
    "url"
  ]
}

Free, 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 OCR). Layout and tables are not preserved. Fails if the URL serves HTML, not a PDF.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Direct link to the .pdf file, not a viewer page. Not with data."
    },
    "data": {
      "type": "string",
      "description": "Base64 PDF, max 5 MB decoded. Not with url."
    },
    "maxChars": {
      "type": "number",
      "description": "Output cap, chars. Default 20000, max 100000."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward (Authorization, Cookie…)."
    }
  }
}

Free, 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,truncated},rows:[{column:value}]}, all values strings, or CSV text with format='csv'. One filter condition, no joins or aggregates. Unknown select columns and bad filters error with the valid names or operators. Over 5 MB: csv_query_xl (paid, 100 MB).

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "CSV URL, max 5 MB. Not with csv."
    },
    "csv": {
      "type": "string",
      "description": "Inline CSV text. Not with url."
    },
    "select": {
      "type": "string",
      "description": "Columns to keep, comma-separated, exact header names. Omit for all."
    },
    "filter": {
      "type": "string",
      "description": "'column op value'. Ops: = != contains startswith endswith (text, case-insensitive), > >= < <= (numeric). E.g. 'age >= 30'."
    },
    "sort_by": {
      "type": "string",
      "description": "Column to sort by; numeric when values parse as numbers, else text."
    },
    "sort_dir": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ],
      "description": "asc (default) or desc."
    },
    "limit": {
      "type": "number",
      "description": "Rows to return. Default 500, max 5000; over it meta.truncated=true."
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "csv"
      ],
      "description": "json (default): {meta,rows}. csv: text with header row."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward (Authorization, Cookie…)."
    }
  }
}

Free, 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)]; no slices or jq. Errors on invalid JSON or over 5 MB (json_query_xl: paid, 25 MB).

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "JSON URL, max 5 MB. Not with json."
    },
    "json": {
      "type": "string",
      "description": "Inline JSON text. Not with url."
    },
    "query": {
      "type": "string",
      "description": "Starts with $: '$.users[*].name', '$..price', '$.items[?(@.price<10)].id'. Filter ops: = != > >= < <= =~. '$' = whole document."
    },
    "limit": {
      "type": "number",
      "description": "Default 100, max 1000. Above it: {results,total,returned}."
    },
    "headers": {
      "type": "object",
      "description": "Headers to forward (Authorization, Cookie…)."
    }
  },
  "required": [
    "query"
  ]
}

Free, 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 sitemaps[] with the child URLs; children are not fetched, call again per child. Uncompressed XML only, no .gz. Errors on non-2xx, 10 s timeout or private hosts.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "sitemap.xml or sitemap index URL, http(s), uncompressed."
    },
    "maxUrls": {
      "type": "number",
      "description": "Default 100, max 1000; urlCount still reports the full total. Ignored for a sitemap index."
    }
  },
  "required": [
    "url"
  ]
}

Free, 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, categories, enclosure. Items past maxItems are dropped and truncated=true. A URL that is not a feed returns type 'unknown' and no items. Not JSON Feed. Errors on non-2xx, 10 s timeout or private hosts.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Feed URL, http(s). Private hosts refused."
    },
    "maxItems": {
      "type": "number",
      "description": "Default 20, max 200. itemCount still reports the full total."
    }
  },
  "required": [
    "url"
  ]
}

Screenshot 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.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Page URL."
    },
    "fullPage": {
      "type": "boolean",
      "default": false,
      "description": "true = whole page, not viewport."
    },
    "width": {
      "type": "number",
      "default": 1280,
      "description": "Viewport px."
    },
    "height": {
      "type": "number",
      "default": 800,
      "description": "Viewport px."
    },
    "format": {
      "type": "string",
      "enum": [
        "png",
        "jpeg"
      ],
      "default": "png",
      "description": "Default png."
    },
    "quality": {
      "type": "number",
      "minimum": 1,
      "maximum": 100,
      "description": "JPEG only, 1-100."
    }
  },
  "required": [
    "url"
  ]
}

Google 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.

Input Schema

{
  "type": "object",
  "properties": {
    "keywords": {
      "type": "array",
      "description": "1-20 keywords."
    },
    "language_code": {
      "type": "string",
      "default": "es",
      "description": "ISO 639-1."
    },
    "location_code": {
      "type": "number",
      "default": 2724,
      "description": "DataForSEO location (default Spain)."
    },
    "include_suggestions": {
      "type": "boolean",
      "default": true,
      "description": "Add related suggestions."
    }
  },
  "required": [
    "keywords"
  ]
}

Remove 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.

Input Schema

{
  "type": "object",
  "properties": {
    "image_url": {
      "type": "string",
      "description": "Public image URL."
    }
  },
  "required": [
    "image_url"
  ]
}

Recommended Prompts

research_workflow

Search for [topic], then get detailed information about the top results using ToolSnap MCP

Expected tools: csv_queryfetch_extract

search_research

Search for information about [topic] using ToolSnap MCP

Expected tools: csv_query

find_specific

Find [specific item] using ToolSnap MCP

Expected tools: csv_query

retrieve_data

Get details about [item] from ToolSnap MCP

Expected tools: fetch_extract

fetch_info

Fetch [information type] using ToolSnap MCP

Expected tools: fetch_extract

Community

Rate this Server

Evidence

Recent observations

Oct 30, 2026, 12:32 PM UTCverifiedversion not recorded17 tools

Oct 21, 2026, 8:32 PM UTCverifiedversion not recorded17 tools

Oct 13, 2026, 8:03 PM UTCverifiedversion not recorded17 tools

Oct 6, 2026, 5:32 AM UTCverifiedversion not recorded17 tools

Sep 28, 2026, 6:32 AM UTCverifiedversion not recorded17 tools

Sep 22, 2026, 9:32 AM UTCverifiedversion not recorded17 tools

ToolSnap MCP

Quality & Safety

Context Cost

One-Click Install

Remote endpoints

Tool inventory

Tools (17)

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Recommended Prompts

Rate this Server

Recent observations