ThirdMade Shelf

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "ThirdMade Shelf": {
      "url": "https://shelf.thirdmade.net/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (26)

• robots

  Parses robots.txt for any domain — shows crawl rules, disallowed paths, sitemaps. Agents use this to check if they're allowed to scrape a site before doing it. [free]

  Parameters:

  • url (required) — string — Target webpage URL

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• llms_txt

  Fetches and normalizes llms.txt / llms-full.txt from any site — the emerging standard for making websites readable to AI agents. [free]

  Parameters:

  • url (required) — string — Target webpage URL

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• page_meta

  Extracts OG tags, canonical URL, title, and meta description from any web page. Useful for link previews, SEO audits, and content enrichment. [price: $0.001/call USDC via x402]

  Parameters:

  • url (required) — string — Target webpage URL

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• domain_facts

  Live-checks a domain: is it up, does it have TLS, what's the title? Quick domain health check for agents evaluating links. [price: $0.001/call USDC via x402]

  Parameters:

  • domain (required) — string — Domain name

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• link_graph

  Extracts all outbound links from a page, classified by domain. Shows where a page links to and which domains dominate. [price: $0.001/call USDC via x402]

  Parameters:

  • url (required) — string — Target webpage URL

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scrape

  Scrapes any public web page and returns clean structured JSON (title, text, length). The workhorse — agents use this for real data extraction. [price: $0.01/call USDC via x402]

  Parameters:

  • url (required) — string — Target webpage URL

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• captcha_eval

  Classifies captcha type (reCAPTCHA, hCaptcha, Turnstile) and difficulty. Eval only — we do NOT solve captchas. [price: $0.01/call USDC via x402]

  Parameters:

  • type — string — Captcha type: recaptcha, hcaptcha, turnstile, image, slider, puzzle

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• geo_time

  Geocode + timezone + currency context for any location string. [price: $0.001/call USDC via x402]

  Parameters:

  • q (required) — string — Location string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• entity_find

  Extracts named entities (people, companies, places) from text. Wikidata resolution next iteration. [price: $0.001/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_verify

  Checks if a URL supports a claim. Returns confidence score. Research agents use this to verify sources. [price: $0.01/call USDC via x402]

  Parameters:

  • url (required) — string — Source URL
  • claim (required) — string — Claim to verify

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• similar_domains

  Finds similar/competitor domains by name-similarity. Lead-gen agents use this for prospecting. [price: $0.001/call USDC via x402]

  Parameters:

  • domain (required) — string — Domain name

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• gas_now

  Current gas prices in Gwei for Base, Ethereum, or Arbitrum via public RPC. [free]

  Parameters:

  • chain — string — base (default), ethereum, or arbitrum

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• chain_stats

  Block height + chain stats for Base or Ethereum. [price: $0.001/call USDC via x402]

  Parameters:

  • chain — string — base (default), ethereum, or arbitrum

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• nonce

  Current transaction nonce for any address on Base or Ethereum. Agent tx bots need this before sending transactions. [price: $0.001/call USDC via x402]

  Parameters:

  • address (required) — string — EVM address
  • chain — string — base (default) or ethereum

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• token_security

  Token security heuristics: honeypot signals, proxy detection, LP data. Trading agents use this to avoid rugs. [price: $0.01/call USDC via x402]

  Parameters:

  • address (required) — string — Token contract address
  • chain — string — base (default)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• ens_lookup

  ENS name resolution + reverse lookup via public Ethereum RPC. [price: $0.001/call USDC via x402]

  Parameters:

  • name (required) — string — ENS name or address

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• summarize

  Extractive summary (3 sentences) + top-5 keywords from any text. [price: $0.001/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• jsonify

  Coerces messy text (key=value lines, CSV-ish, sentences) into clean JSON. [price: $0.001/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• sentiment

  Sentiment classification (positive/negative/neutral) + emotion keyword hits. [price: $0.001/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• image_gen

  Generates 1 PNG from a text prompt (FLUX.1-dev, 512px). Async: returns job ID + poll URL. GPU-backed via RunPod ComfyUI, scale-to-zero. [price: $0.02/call USDC via x402]

  Parameters:

  • prompt (required) — string — Image prompt

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• image_status

  Poll image-gen job status by job ID. Returns image base64 PNG when COMPLETED. [free]

  Parameters:

  • job (required) — string — Job ID from image_gen

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• pii_guard

  Detects PII (emails, phones, SSNs, credit cards) in any text with character spans. Compliance agents use this before processing user data. [price: $0.001/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• prompt_guard

  Scores prompt-injection / jailbreak risk for LLM inputs. Agent builders use this to sanitize user inputs before hitting their LLM. [price: $0.01/call USDC via x402]

  Parameters:

  • text (required) — string — Input text

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• hallucination_check

  Entailment scoring: does the provided context support this claim? Research agents use this to self-check outputs. [price: $0.001/call USDC via x402]

  Parameters:

  • context (required) — string — Evidence/context text
  • claim (required) — string — Claim to check

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• json_guard

  Validates JSON, detects PII inside values, reports schema stats. Pipeline agents use this as a data-quality gate. [price: $0.001/call USDC via x402]

  Parameters:

  • json (required) — string — JSON text to validate

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• sweep

  One verify-loop lane: confidence-labeled findings on any topic. The flagship teaser — full sweeps at $0.50-5 ship when this crosses BUILD. [price: $0.05/call USDC via x402]

  Parameters:

  • topic (required) — string — Research topic

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.