ToolSnap MCP
ToolSnap MCP gives agents deterministic, context-efficient web/data/media microtools with compact discovery and pay-per-call execution.
Browse all 47 tools by family or name via
tool_catalog, then run any catalog tool throughuse_tool.Check costs/payment options with
pricing, get workflow prompts fromtask_recipes, and retrieve memory-setup text frommemory_snippet.Fetch public URLs as clean text (
fetch_extract), raw HTML (fetch_html), Markdown (html_to_markdown), or head metadata/OG/JSON-LD (fetch_metadata).Extract text from PDFs and query CSV or JSON from URLs or inline data.
Parse XML sitemaps and RSS/Atom feeds.
Use paid tools such as screenshots, keyword research, and background removal; unpaid calls return a structured x402 payment challenge.
Free tools work immediately; paid calls use USDC on Base via x402, prepaid credits, or an API key.
Enables AI agents to pay for tool calls using USDC on Base via the x402 payment protocol (Coinbase's infrastructure). Supports first-call-free per wallet, prepaid balances with discounted per-call pricing, and automatic payment retry upon 402 response.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
ToolSnap MCP
One connection, superpowers for your agent: deterministic microtools. Pay per call with USDC on Base — no account needed — or buy fiat credits with a card if you'd rather not touch crypto.
Live endpoint: https://mcp.toolsnap.app/mcp
Server card: /.well-known/mcp.json
Pricing: /.well-known/pricing.json
Docs: mcp.toolsnap.app/docs
Why
ToolSnap is built around three ideas:
1. Deterministic — no LLM in the loop. Most agent stacks now "clean" web pages by paying a second model to summarize them. ToolSnap's extraction is pure parsing: exact quotes, stable output, zero added inference cost, reproducible runs. What you extract is what the page said.
2. Context-efficient by design. The biggest cost for AI agents isn't generation — it's context. Loading a raw webpage can burn 50,000+ tokens on HTML boilerplate; connecting a fat MCP server can burn as many in tool definitions. ToolSnap moves the work server-side and keeps discovery compact: tools/list shows a small curated core, and the full catalog of 47 microtools (web, PDFs, CSV/JSON, sitemaps, RSS, images, media generation…) sits one free tool_catalog() call away, executed via use_tool.
Benchmark (11 real pages, June 2026):
Raw HTML | Extracted | Saving | |
Median tokens | 53,820 | 2,001 | 98.1% |
Cost @ Sonnet ($3/M) | $0.162 | $0.006 | $0.156/call |
Break-even page size | — | — | 26 KB |
fetch_extract is free — this saving costs nothing.
3. No account required (crypto path). Free tools work the second you connect. Paid tools settle per call with USDC on Base via x402 — an agent with a wallet can pay cold: no signup, no subscription, no key management. Rather not touch crypto? Buy fiat credits with a card and get an API key instead — same discounted per-call price, no wallet needed.
Related MCP server: Local SEO Data
Connect
Any agent, one line
Hand your agent this prompt and it can do the rest on its own:
Set up https://mcp.toolsnap.app/SKILL.md — connect the MCP server it describes and save the skill for future sessions.SKILL.md is a self-contained skill file (connect
config, tool discovery, cost guardrails), generated live from the tool registry so it is
never stale.
Claude Desktop
{
"mcpServers": {
"toolsnap": {
"url": "https://mcp.toolsnap.app/mcp",
"transport": "streamable-http"
}
}
}Free tools work immediately with the URL connection above. Paid tools need an
x402 payment client — a wallet alone is not enough, because most MCP clients
can't satisfy a 402 Payment Required on their own. Use the pay-proxy below (re-download it if your copy predates the 2026-10 spec-shaped 402, see Payment).
Claude Code
claude mcp add --transport http toolsnap https://mcp.toolsnap.app/mcpOr install the Claude Code plugin
(MCP connection + the toolsnap skill, bundled):
/plugin marketplace add ToolSnap-app/toolsnap-claude-plugin
/plugin install toolsnapPaid tools — connect through the pay-proxy
scripts/pay-proxy.mjs is a local stdio MCP server that wraps the remote
endpoint, reads your wallet, and signs + retries automatically when the server
asks for payment. The private key never leaves your host; only signatures are sent.
{
"mcpServers": {
"toolsnap": {
"command": "node",
"args": ["/ABSOLUTE/PATH/to/toolsnap-mcp/scripts/pay-proxy.mjs"]
}
}
}No wallet yet? Call the wallet_setup tool — it generates a wallet you control,
helps your human fund it with USDC on Base, and wires this proxy. Key resolution
order: TOOLSNAP_WALLET_KEY → ~/.toolsnap/wallet.key → macOS Keychain
(toolsnap-agent-wallet/default).
Useful env: TOOLSNAP_MAX_PRICE_USDC (per-call spend cap, default 0.10),
TOOLSNAP_PREPAID=1 + TOOLSNAP_AUTO_DEPOSIT_USDC (use the cheaper prepaid balance).
Paid tools — no wallet, pay with a card
Buy credits at mcp.toolsnap.app/checkout (handled by Polar, our Merchant of Record). You'll get an API key in a one-time pop-up — connect with it directly, no proxy needed:
{
"mcpServers": {
"toolsnap": {
"url": "https://mcp.toolsnap.app/mcp",
"headers": { "Authorization": "Bearer sk_live_..." }
}
}
}Clients that can't send custom headers (some claude.ai connectors) can embed
the key in the URL instead: https://mcp.toolsnap.app/mcp/sk_live_... (the
key may then appear in that client's request logs — prefer the header when
your client supports it).
Direct MCP call
curl -X POST https://mcp.toolsnap.app/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Tools
47 tools total. tools/list shows a curated core of 17; discover everything else with the free tool_catalog tool and run it with use_tool(name, args).
Paid (x402)
Tool | Description | Price |
| Capture a page → public image URL. | $0.04 USDC |
| Render a JS page (SPA) in a headless browser → clean text. | $0.04 USDC |
| Google Ads volume/CPC/competition via DataForSEO. | $0.04 USDC |
| Remove an image's background → transparent PNG URL. | $0.03 USDC |
| Text-to-image via fal.ai FLUX. | from $0.02 USDC |
| 2x/4x super-resolution via fal.ai ESRGAN. | from $0.02 USDC |
| Speech-to-text via fal.ai Wizper. | from $0.02 USDC |
| Text-to-speech via fal.ai Kokoro. | from $0.02 USDC |
| Async text/image-to-video via fal.ai. | from $0.08 USDC |
| Query URL-hosted CSV (5–100 MB) / JSON (5–25 MB). | $0.02 USDC |
No first-call-free: these tools have real per-call cost, so every call settles from the start. Media tools are priced per call from your own args (the table shows the floor). Pay-per-call is USDC on Base using x402 v2 (EIP-3009 transferWithAuthorization); prepaid (deposit once, debit off-chain, crypto or card) is cheaper per call.
Free (always)
Flagship: fetch_extract (URL → clean text, median 98.1% fewer tokens than raw HTML) and fetch_html (URL → clean structured HTML). Plus a wide utility catalog:
Tool | Description |
| Machine-readable pricing menu. Call this first. |
| Discover the full tool catalog (families → detail). |
| Execute any tool not in your tools/list. |
| Get the ToolSnap habit block for your harness's persistent memory. |
| Ready-to-run multi-tool workflows for whole tasks. |
| 1–100 random UUID v4 values |
| SHA-256 / SHA-1 / SHA-512 (hex) |
| Base64 encode/decode |
| Percent-encode/decode |
| Parse + pretty-print or minify JSON |
| Unix ↔ ISO 8601 (auto-detects direction) |
| Chars, words, lines, sentences |
Call tool_catalog() for the complete, current list with schemas and prices.
Payment (x402)
When an agent calls a paid tool (e.g. screenshot_url) without payment, the server returns a tool result in the x402 v2 MCP transport shape: isError: true, the payment requirements in structuredContent, and the same object JSON-encoded in content[0].text (a second text block carries the next steps):
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"isError": true,
"structuredContent": {
"x402Version": 2,
"error": "Payment required to use this tool",
"resource": { "url": "https://mcp.toolsnap.app/mcp#screenshot_url", "serviceName": "ToolSnap" },
"accepts": [{
"scheme": "exact",
"network": "eip155:8453",
"amount": "40000",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"payTo": "0x…",
"maxTimeoutSeconds": 300
}],
"extensions": { "bazaar": { "info": { "input": { "type": "mcp" } } } }
},
"content": [{ "type": "text", "text": "<the same JSON>" }, { "type": "text", "text": "Payment required: …" }]
}
}Until 2026-10 this was a JSON-RPC error (error.code: 402, error.data). If you downloaded scripts/pay-proxy.mjs before then, download it again: older copies only recognise the old shape and will not pay on their own. (The prepaid-deposit challenge, account_deposit, still answers with the JSON-RPC 402 error.)
An x402-enabled client reads accepts[0], signs an EIP-3009 TransferWithAuthorization, and retries with _meta["x402/payment"] set. See x402 spec.
Run locally
npm install
cp .dev.vars.example .dev.vars # fill in wallet secrets
npm run dev
# Worker at http://localhost:8787Type-check
npm run typecheckDeploy
npm run deployProduction deploys come from .github/workflows/deploy.yml (push to main).
Alerta de despliegues inesperados
Vigila que nadie publique toolsnap-mcp ni toolsnap-portal fuera del workflow (acción A14 del plan de seguridad). Corre en el cron de 5 minutos que ya existe (src/alerts/deploy-watch.ts): lee los últimos deployments de cada Worker por la API de Cloudflare con un token de solo lectura y, si hay uno nuevo que no está registrado como esperado, avisa por Telegram (el canal de las demás alertas) con Worker, deployment, versión, fecha, author_email, origen y mensaje. La primera pasada sin estado solo guarda el último deployment. Un rollback avisa siempre, esté o no registrado.
Lo esperado vive en el KV X402_NONCES: esperado:{worker}:dep:{deploymentId} (caduca a los 90 días) y ultimo-visto:{worker}. Se registra el deployment y no la versión a propósito: un wrangler rollback crea un deployment nuevo con una versión ya conocida. El workflow registra el suyo tras wrangler deploy. Cualquier otra cosa avisa, también un wrangler secret put (crea una versión nueva): si lo has hecho tú, regístralo. Si el aviso no consigue salir por Telegram se reintenta cada pasada y, pasada 1 hora, el cron falla y lo ve /analytics (tarea deploy-watch).
Deploy manual desde el Mac (o tras un wrangler secret put):
CLOUDFLARE_API_TOKEN=... scripts/registrar-deploy.sh toolsnap-mcpHazlo en los tres minutos siguientes al deploy: es el margen de cortesía antes de que la alerta salga. toolsnap-portal se despliega desde otro repositorio: su workflow tiene que llamar a este mismo script con toolsnap-portal.
Qué hay que poner (una sola vez):
npx wrangler secret put VIGIA_CF_TOKEN
# TELEGRAM_BOT_TOKEN y TELEGRAM_CHAT_ID ya existen (alertas de error); no hay que tocarlos.VIGIA_CF_TOKEN: token de solo lectura en la cuenta ToolSnap con el permiso Workers Metadata Read-Only (la documentación de la API lo acepta paraGET .../deployments; no es el de «Workers Scripts Read», que además permite descargar el código de todos los Workers). Sin el secret, la vigilancia no hace nada.El token
CLOUDFLARE_API_TOKENdel environmentproductionde GitHub necesita además Workers KV Storage: Edit (cuenta ToolSnap) para el paso «Register deployment as expected» (y parascripts/registrar-deploy.sh); sin él, cada deploy dará una alerta. Pon el secret y el permiso antes de fusionar.VIGIA_WORKERSincluye tambiéntoolsnap-x-personal(Worker de los tokens personales de X, A16), cuyo jobdeploy-x-personalregistra su deployment con el tokenCLOUDFLARE_API_TOKEN_X_PERSONAL. Ese token (Editor solo de ese Worker) necesita además Workers KV Storage: Edit (cuenta ToolSnap) para escribir enX402_NONCES. Dáselo antes de fusionar, como se hizo con el token principal: hasta entonces el paso «Register deployment as expected» de ese job falla sin cortar el deploy (continue-on-error) y cada merge amainhace saltar una alerta de la vigilancia portoolsnap-x-personal. Con el permiso de KV el token puede escribir en el mismo KV que usa el vigilante: es el coste de vigilar ese Worker con la misma lista de esperados.
Límite estructural. El vigilante corre dentro de toolsnap-mcp, que es uno de los vigilados, y el repositorio es público: quien pueda desplegar toolsnap-mcp puede quitar la llamada, escribir ultimo-visto y esperado:* en el KV y leer VIGIA_CF_TOKEN. Cubre un deploy descuidado del socio y cualquier deploy de toolsnap-portal; no cubre a un adversario con permiso de deploy sobre toolsnap-mcp. Para eso haría falta vigilar desde fuera (un schedule de GitHub Actions o un Worker aparte con su propio KV y token).
Stack
Runtime: Cloudflare Workers (edge, 0 ms cold start)
Protocol: MCP streamable-http (JSON-RPC 2.0)
Payment: x402 v2 · EIP-3009 on Base mainnet · USDC
Verification: off-chain EIP-712 signature recovery (viem)
Settlement: on-chain
transferWithAuthorizationvia relayer walletAnti-replay: Cloudflare KV nonce store (7-day TTL)
First-call-free: mechanism exists in code (KV key
first_free:{address}) for future flat-rate tools; all current paid tools have real COGS and are excluded, so every call settles
Contributing
PRs welcome for new free tools in src/tools/. Follow the pattern in src/tools/text-stats.ts and add the tool to src/tools/index.ts.
For paid tools or changes to the x402 payment logic, open an issue first.
Do not commit wallet private keys, .dev.vars, or any secrets.
License
MIT
Available Tools
17 toolscsv_queryQuery CSVARead-onlyInspect
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).
Inputs: csv, url, limit, filter, +5 more.
fetch_extractFetch page as clean textARead-onlyInspect
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.
Inputs: url (required), headers, maxChars.
fetch_htmlFetch raw HTMLARead-onlyInspect
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.
Inputs: url (required), headers, maxChars.
fetch_metadataFetch page metadataARead-onlyInspect
Free, read-only. Fetch a public http(s) URL and return its 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).
Inputs: url (required), headers.
html_to_markdownConvert HTML to MarkdownARead-onlyInspect
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.
Inputs: url, html, headers, maxChars.
json_queryQuery JSONARead-onlyInspect
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).
Inputs: query (required), url, json, limit, +1 more.
keyword_researchKeyword researchARead-onlyInspect
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.
Inputs: keywords (required), language_code, location_code, include_suggestions.
memory_snippetMemory snippet for agentsARead-onlyInspect
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.
Inputs: harness.
pdf_text_extractExtract PDF textARead-onlyInspect
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.
Inputs: url, data, headers, maxChars.
pricingPricing and payment optionsARead-onlyInspect
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.
Inputs: no named parameters.
remove_backgroundRemove image backgroundAInspect
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.
Inputs: image_url (required).
rss_parseParse RSS or Atom feedARead-onlyInspect
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.
Inputs: url (required), maxItems.
screenshot_urlScreenshot a URLAInspect
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.
Inputs: url (required), width, format, height, +2 more.
sitemap_parseParse sitemapARead-onlyInspect
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.
Inputs: url (required), maxUrls.
task_recipesTask recipesARead-onlyInspect
Free. Multi-tool workflow prompts (clone a site, SEO audit). No args → menu; recipe='' → prompt.
Inputs: recipe.
tool_catalogBrowse tool catalogARead-onlyInspect
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='': each tool with name, price, description, notes, inputSchema. tool='': that entry alone; wins over family. Unknown ids error naming the valid families. Run what you find via use_tool.
Inputs: tool, family.
use_toolRun any catalog toolAInspect
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='') first. A missing or unknown name errors pointing to tool_catalog; it cannot call itself.
Inputs: name (required), args.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools target clearly distinct resource/action combinations, and descriptions explicitly route between similar tools. There is still some overlap between fetch_html, fetch_extract, and html_to_markdown, and use_tool is a generic wrapper that could be confused with direct calls, though the descriptions mitigate this.
All names use snake_case and are readable, but the naming patterns are mixed: fetch_html, csv_query, sitemap_parse, memory_snippet, pricing, and html_to_markdown do not follow one predictable verb_noun or resource_action convention. This is mixed but still understandable rather than chaotic.
Seventeen tools is slightly above the typical ideal range, but the server covers a broad set of extraction, metadata, pricing, catalog, and paid utility functions. Each top-level tool has a reasonably distinct role, though a few fetch variants could potentially be consolidated.
The surface covers the main web/data extraction formats (HTML, text, metadata, Markdown, PDF, CSV, JSON, sitemap, RSS) plus catalog, pricing, recipes, screenshots, and a wrapper for missing catalog tools. Minor gaps remain around OCR, direct JS rendering, and large-file query variants, but these are documented or reachable through the catalog wrapper.
Maintenance
Related MCP Connectors
Pay-per-use MCP tools for AI agents. USDC on Base via x402. No API keys.
Pay-per-fetch web extraction for agents: POST a URL, get clean markdown. x402 USDC on Base.
Pay-per-call web tools for agents (extract, summarize, ask, JSON) via x402 USDC on Base.
Pay-per-request webpage-to-Markdown extraction for AI agents. $0.005 USDC via x402 on Solana.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown.45,464 npm837MIT

Local SEO Dataofficial
AlicenseAqualityBmaintenance42 local SEO tools for AI assistants. SERP tracking, Google Business Profile data, review monitoring, keyword research, AI visibility scoring, geogrid rank scans, citation audits, and competitive analysis.5353 npm3MIT- AlicenseAqualityBmaintenanceRead any public web page, or up to 20 in one batch, as a clean AIDocument: Markdown plus title, description, structure, and provenance, with navigation and boilerplate stripped. Reads are served through Lyrenth's own independently built web index, so each costs a fraction of the tokens of raw HTML and is origin-friendly. A third tool reports your plan and how many reads you have used.3103 npm1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server providing 17 keyless, pay-per-use web-data tools with signed-provenance receipts, enabling AI agents to autonomously fetch, extract, and verify web content on Base mainnet.48 npmMIT