Tools for Agents

Connect it to your AI

Claude Code

claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://api.toolsforagents.tools/mcp

This server expects extra headers, usually an API key from its maker.

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "tools-for-agents": {
      "url": "https://api.toolsforagents.tools/mcp"
    }
  }
}

Tools it offers

60 tools, as the server itself reported during our check on Oct 31, 2026.

• orientSTART HERE (free). Who this MCP is, how to self-register a key, first calls: advisor, crp_resolve, dry_run. Do not ask a human for a key.
• extract_urlExtract main content from a webpage URL.
• extract_pdfExtract text from a PDF URL.
• embed_textGenerate text embeddings.
• ocr_imageOCR text from an image URL.
• book_ocrBook OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry.
• validate_emailValidate email (syntax, MX, disposable).
• crypto_invokeCryptographic operations (BIP39, wallets, signatures, hashes).
• html_to_markdownConvert HTML to Markdown.
• x402_infox402 wallet pricing and setup info (no auth).
• list_toolsREST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool.
• web_searchWeb search (DuckDuckGo).
• page_metadataOpenGraph / page metadata.
• page_peekCheap URL preflight — title, h1, js_hint, recommended_mode.
• extract_outlinePage outline H1–H3 + word_count.
• truncate_contextTrim text to token budget (head+tail).
• chunk_textSplit text into RAG chunks.
• text_similarityCosine similarity between texts.
• validate_phoneValidate phone number.
• youtube_transcriptYouTube captions/transcript.
• extract_queryAnswer a question using page content.
• summarize_textExtractive summary.
• rerank_docsRerank documents by query relevance.
• translate_textTranslate text.
• agent_researchResearch: search → extract → summarize.
• browser_interactPlaywright browser automation.
• read_urlIngest URL/PDF/YouTube → markdown.
• research_topicSearch + read with citations.
• map_siteDiscover site URLs.
• estimate_costEstimate API units (free).
• memory_storeStore session memory note.
• memory_searchSearch session memory.
• validate_urlCheck URL reachability.
• extract_linksList links from page.
• json_ldJSON-LD from URL.
• readabilityClean article text.
• extract_schemaStructured fields from JSON-LD.
• extract_jsonStructured JSON from URL.
• cache_urlCached extract (0 units on hit).
• retrieveSemantic retrieval top-k.

Questions