Tools for Agents

🚀 58+ REST tools · 44 MCP tools · 5,000 FREE req/day!

CommunityOnlineNo sign-inRU / CISFreeCan modify data

What it can do

  • Extract Url: Extract main content from a webpage URL as markdown or text.
  • Extract Pdf: Extract text from a PDF file by URL.
  • Embed Text: Generate text embeddings (minilm 384d or bge-large 1024d).

What data it sees

Do you need an account

No: the server works without sign-in

🚀 58+ REST tools · 44 MCP tools · 5,000 FREE req/day! Agent Advisor, extract, PDF, OCR, summarize, bias/conflict detection. Self-register in 0.7s — POST /v1/register {} (no email).

Remote Streamable HTTP MCP for autonomous AI agents.

FREE TIER (growth phase): • 5,000 requests / day • 120 requests / minute • 500 GPU units / month • Instant API key: POST https://api.toolsforagents.tools/v1/register with {} • No credit card · no human signup

MCP LAYER (44 tools at /mcp): • Web: extract_url, read_url, screenshot, crawl, cache_url • Search/RAG: web_search, agent_research, retrieve, chunk_text • Media: extract_pdf, ocr_image, youtube_transcript • Text: summarize_text, translate_text, compare_texts • Platform: list_tools, estimate_cost, memory_store

FULL REST API (58+ tools): • Agent Advisor, dry-run, confidence/estimate, conflict/detect • Commons collective memory, bias detection, workflows • OpenAPI: https://api.toolsforagents.tools/docs

QUICK START (no npm required): Cursor ~/.cursor/mcp.json: { "mcpServers": { "tools-for-agents": { "type": "streamable-http", "url": "https://api.toolsforagents.tools/mcp", "headers": { "Authorization": "Bearer sk_live_..." } } } }

Copy-paste configs: https://github.com/max124vip-dev/tools-for-agents/tree/main/mcp-configs MCP Quick Start: https://github.com/max124vip-dev/tools-for-agents/blob/main/docs/MCP_QUICKSTART.md

Onboarding: https://api.toolsforagents.tools/v1/onboarding Full agent guide: https://toolsforagents.tools/docs/guide GitHub: https://github.com/max124vip-dev/tools-for-agents Website: https://toolsforagents.tools

Optional: x402 pay-per-call (USDC) without registration

How to connect

How to connect Tools for Agents to Claude

The server address to paste into Claude settings:

https://toolsforagents--max124vip.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Tools for Agents to ChatGPT

The server address to paste into ChatGPT settings:

https://toolsforagents--max124vip.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Tools for Agents to Cursor

The server address to paste into Cursor settings:

https://toolsforagents--max124vip.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (44)

Raw names from tools/list. Only developers need these.

extract_urlExtract main content from a webpage URL as markdown or text.
extract_pdfExtract text from a PDF file by URL.
embed_textGenerate text embeddings (minilm 384d or bge-large 1024d).
ocr_imageOCR text from an image URL.
validate_emailValidate an email address (syntax, MX, disposable check).
crypto_invokeExact cryptographic math: BIP39 mnemonics, BTC+ETH wallets, addresses, Bitcoin message signatures, Ethereum EIP-191, SHA-256, Keccak-256. Use when a human asks their AI for wallet keys, mnemonics, addresses, or signatures.
html_to_markdownConvert HTML string to Markdown.
x402_infox402 agent wallet: pricing, network, setup (testnet faucets / mainnet CDP). No auth required.
list_toolsList available AgentTools API endpoints and unit pricing.
web_searchWeb search (DuckDuckGo) — find URLs and snippets for a query.
page_metadataOpenGraph / title / favicon metadata for a URL.
chunk_textSplit long text into RAG chunks with overlap.
text_similarityCosine similarity between 2+ texts (uses embed GPU).
validate_phoneValidate phone number (E.164, carrier, type).
youtube_transcriptFetch YouTube video transcript/subtitles.
extract_queryAnswer a question using content from a webpage URL.
summarize_textExtractive summary of long text.
rerank_docsRerank documents by relevance to a query.
translate_textTranslate text to target language.
agent_researchResearch pipeline: search → extract → summarize.
browser_interactPlaywright browser steps: click, fill, text, screenshot, wait.
read_urlAgent-first: ingest URL/PDF/YouTube → markdown + token_estimate + next_actions (~2 units).
research_topicAgent-first: search + read top pages with citations (~10 units).
map_siteDiscover URLs on a site via sitemap or links.
estimate_costEstimate API units/tokens before calling a tool (free).
memory_storeStore a key-value note in agent session memory.
memory_searchSearch agent session memory by query.
validate_urlCheck if a URL is reachable and get final redirect URL.
extract_linksList links from a webpage.
json_ldExtract JSON-LD structured data from a URL.
readabilityExtract clean article text with token estimate.
extract_schemaExtract structured fields from JSON-LD on a page.
extract_jsonStructured JSON from URL (JSON-LD + heuristics).
cache_urlGet cached extract for URL (0 units on cache hit).
retrieveSemantic top-k document retrieval by query.
screenshotCapture webpage screenshot as PNG base64.
batch_extractBatch extract up to 50 URLs (async job).
crawlDiscover site URLs and batch-extract (async job).
job_statusPoll async batch/crawl job status.
monitor_urlCreate URL change monitor with optional webhook.
compare_textsCompare two texts or URLs.
ocr_tableOCR with table layout from image URL.
image_describeDescribe image content (vision).
transcribe_audioTranscribe audio/video from URL.