_ registry / a2a + mcp streamable-http · checked 39d ago

MERCURY Web Fetch

https://mercury-x402-jed.fly.dev

Registry code: ea575f91f781c998

api record

The keyless, signed-provenance web-fetch for autonomous agents. Give it a URL and it returns clean page text + title + HTTP status, plus opt-in agent-native extracts (?format=markdown, ?links=1 link-graph, ?extract=1 description+wordCount). The wedge over free/keyed scrapers (Jina/Firecrawl/Tavily): every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) you can verify OFFLINE — and an agent onboards itself with zero humans, paying in-band over HTTP 402. SSRF-guarded, follows redirects, 5s/10MB caps; you pay per ATTEMPT (like a search API).…

endpoint
https://mercury-x402-jed.fly.dev/mcp
door code
823296cc3ab62f69
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is MERCURY Web Fetch live?
Yes — it answered the hub's last check (checked 39d ago). It answered 100% of checks over the last 30 days.
Is MERCURY Web Fetch free to use?
Yes — the hub reached it with no key and no payment.
What tools does MERCURY Web Fetch have?
18 tools: headers, links, diff, table, validate, batch, sitemap, dns, ….
Is MERCURY Web Fetch safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.8%

90 days 99.4%· all time 99.2%

latency
677ms

last good check

priced tools
2

of 18 tools

_ answered our checks, 90 days 904 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
search & web scraping & fetch
used for
  • fetch a web page as clean text
  • get a signed provenance receipt for a fetch
  • extract links from a page
takes → gives
web pages → text, data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 18 tools
2 paid 16 never probed 2 of 18 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • fetch 0.003 USDC paid never probed

    VERIFIABLE keyless web-read for autonomous agents. Every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) — the wedge a free scraper structurally CANNOT match: Jina r.jina.ai is free+keyless too, but its bytes are HEARSAY (no proof of what/where/when). MERCURY's `attestation` is ecrecoverable OFFLINE, forever, by you OR any downstream agent you forward the bytes to — proving the content is genuine + untampered (key pinned at /.well-known/mercury-attestation). For RAG, trading and agent-to-agent commerce that need provenance, that is the gap between data and evidence. Beyond that it's the keyless web-read primitive — NO API key, NO signup, NO account, NO monthly plan, the one fetch SKU a fresh agent can onboard to by itself instead of stopping to ask a human for a key. Give a ?url= and get back clean readable page text + title + status. Agent-native extras (opt-in): ?format=markdown for structure-preserving markdown, ?links=1 for an outbound-link graph (crawl frontier), and the headline wedge — STRUCTURED EXTRACT: ?extract=title,price,author,publishedAt returns a clean JSON record { title, price, author, publishedAt }, an LLM-ready row not a wall of text. That is Firecrawl's paid 'JSON mode' (they need an LLM call + an API key for it) done here DETERMINISTICALLY from the page's own JSON-LD/OpenGraph/meta/microdata — keyless, no LLM, $0.003. (?extract=1 still returns the legacy description + wordCount.) The extracted record is folded into the SIGNED attestation too, so a buyer can prove the FIELDS — not just the raw bytes — are exactly what MERCURY resolved. You pay in-band over HTTP 402 (x402, USDC on Base mainnet) — the wedge those tools can't match: they ALL gate behind a human-created API key + a credit-card plan, so an agent can't onboard itself. This one an agent finds in the x402 Bazaar and pays with zero human in the loop. Honest charge-per-ATTEMPT: every call returns a structured result (success OR an ok:false failure with a reason) — never a silent charge-then-500. Follows redirects, SSRF-guarded, 5s timeout, 10MB cap. Pure data, no mint — delivers in prod. — $0.003/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to fetch (http/https)"
    },
    "links": {
      "enum": [
        "0",
        "1"
      ],
      "type": "string",
      "description": "1 = also return the outbound-link graph (crawl frontier)"
    },
    "format": {
      "enum": [
        "text",
        "markdown"
      ],
      "type": "string",
      "description": "text (default) or structure-preserving markdown"
    },
    "extract": {
      "type": "string",
      "maxLength": 256,
      "description": "1 = page description + wordCount; OR a comma-list of field names (e.g. title,price,author,publishedAt) to get a structured JSON record under `extract`"
    }
  },
  "additionalProperties": false
}
    arguments 35 lines
  • markdown 0.005 USDC paid never probed

    URL → clean, LLM-ready markdown (boilerplate/nav/ads stripped, headings + lists + links preserved) with a signed provenance receipt pinning the markdown to its source — the RAG-ingest primitive. Deterministic (no LLM): same URL + same source bytes ⇒ byte-identical markdown. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to convert to markdown (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • headers unknown never probed

    URL → a deterministic HTTP security-headers audit (HSTS, CSP, X-Frame, X-Content-Type, Referrer-Policy, Permissions-Policy + more) with a letter grade and concrete findings, wrapped in a signed, offline-verifiable provenance receipt. Keyless, no LLM, no signup. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page/endpoint to audit (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • links unknown never probed

    URL → a SIGNED outbound/internal link graph: every <a href> as an absolute URL + anchor text, classified internal vs external against the page origin, grouped by origin with a third-party-origin histogram (privacy-audit) and same/cross-origin counts (SEO). Deterministic — same page bytes ⇒ byte-identical graph; no LLM. Covers <a> hyperlinks only (not rel/asset tags). Receipt = EIP-191 over the graph. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to map (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • diff unknown never probed

    URL + prior content-hash (or prior text) -> refetch, deterministic change-proof: changed? + a NEW signed receipt binding fromHash->toHash. Stateless; receipts chain into a tamper-evident audit trail of a page's evolution. Keyless x402, Base mainnet USDC. — $0.006/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to re-fetch + diff (http/https)"
    },
    "format": {
      "enum": [
        "text",
        "markdown"
      ],
      "type": "string",
      "description": "compare cleaned text (default) or structure-preserving markdown"
    },
    "prevHash": {
      "type": "string",
      "maxLength": 66,
      "description": "prior content hash (0x + 64 hex sha256) from an earlier MERCURY fetch/diff receipt. Gives a hash-only change-proof (changed? true/false). Use this OR prevText."
    },
    "prevText": {
      "type": "string",
      "maxLength": 262144,
      "description": "prior page text to diff against. Gives a full deterministic line-level diff (added/removed counts + unified-style hunk) on top of the change-proof. Use this OR prevHash."
    }
  },
  "additionalProperties": false
}
    arguments 32 lines
  • table unknown never probed

    URL in → the page's main HTML <table>(s) parsed into typed, header-keyed rows (JSON) + clean RFC-4180 CSV, with a signed provenance receipt over the exact extracted grid. Deterministic, keyless, no LLM — x402, USDC on Base mainnet. — $0.006/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to extract tables from (http/https)"
    },
    "table": {
      "type": "string",
      "maxLength": 8,
      "description": "optional: 0-based index of a SINGLE table to return (document order). Omit to return ALL tables found (up to the cap)."
    },
    "format": {
      "enum": [
        "both",
        "json",
        "csv"
      ],
      "type": "string",
      "description": "optional: which serialisations to include in `data` (default: both)."
    }
  },
  "additionalProperties": false
}
    arguments 28 lines
  • validate unknown never probed

    URL (a JSON/API endpoint) + a JSON Schema in → a deterministic pass/fail with per-field errors (missing/wrong-type/enum/range/pattern), plus a signed provenance receipt binding the verdict to the exact response bytes AND the exact schema. Deterministic, keyless, no LLM — x402, USDC on Base mainnet. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url",
    "schema"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the JSON/API endpoint to fetch + validate (http/https)"
    },
    "schema": {
      "type": "string",
      "maxLength": 16384,
      "description": "the JSON Schema to validate against. THREE accepted forms: (1) COMPACT URL-native comma list of field[:type] (type in string|number|integer|boolean|array|object|null; default string), e.g. id:integer,name,price:number,inStock:boolean — every field becomes a REQUIRED typed property; (2) a JSON-Schema string (Draft-07 core subset: type/required/properties/items/enum/const/min*/max*/pattern/format/additionalProperties/nullable/anyOf/oneOf/allOf/not); (3) a shorthand-map string {\"id\":\"integer\",\"name\":\"string\"}."
    },
    "pointer": {
      "type": "string",
      "maxLength": 256,
      "description": "optional JSON-Pointer (e.g. /data or /result/0) to validate a SUB-DOCUMENT of the response instead of the whole body (for APIs that wrap the payload)."
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • batch unknown never probed

    List of URLs (≤20) → clean content for each + ONE signed receipt committing to a MERKLE ROOT over every page's contentHash. Tamper-evident multi-page snapshot with per-page membership proofs (selective disclosure). Deterministic (no LLM): same URL set + same source bytes ⇒ byte-identical root + proofs. SSRF-guarded per url; keyless x402, USDC on Base mainnet. — $0.02/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": "string",
      "maxLength": 65536,
      "description": "comma- OR newline-separated list of pages to snapshot (http/https), ≤20 (deduped, capped). Each is fetched through the shared SSRF-guarded engine and becomes one Merkle leaf."
    },
    "format": {
      "enum": [
        "text",
        "markdown"
      ],
      "type": "string",
      "description": "clean text (default) or structure-preserving markdown for every page"
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • sitemap unknown never probed

    Domain/URL → a SIGNED snapshot of the site's PUBLISHED sitemap: discovers the sitemap via robots.txt Sitemap: lines then /sitemap.xml fallback, parses <urlset> + <sitemapindex> (follows up to 5 child sitemaps), returns a deduped, bounded (≤2000) URL inventory with lastmod/changefreq/priority. The receipt signs the DECLARED URL list (deterministic — same sitemap bytes ⇒ byte-identical list). Optional ?fetch=N (≤10) adds a HARD-BOUNDED same-domain liveness probe (title+status+bytes per URL) — that probe is the ONLY non-deterministic part and is NOT covered by the signature. SSRF-guarded; the crawl is bounded at every axis. — $0.01/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "a domain (example.com) or any URL on the site — only its origin is used"
    },
    "fetch": {
      "type": "string",
      "maxLength": 3,
      "description": "optional N (0–10): also shallow-fetch the first N same-domain sitemap URLs and report each one's live title + HTTP status + byte size (liveness sample). NOT covered by the signed receipt (it can change between calls). Default 0 = off."
    },
    "limit": {
      "type": "string",
      "maxLength": 4,
      "description": "optional cap on URLs returned (1–2000); default returns all up to 2000"
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • dns unknown never probed

    Domain → a SIGNED, timestamped DNS snapshot (A, AAAA, MX, NS, TXT, CNAME, SOA), normalised + sorted into a byte-stable record set with an offline-verifiable provenance receipt — proving exactly what the zone resolved to at that moment. Keyless, no LLM, no signup. (Normalisation is deterministic; DNS itself is mutable across time/TTL/geo — which is the very reason the snapshot is timestamped + signed.) — $0.006/call

    mcp-tool

    {
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "alternative to ?domain= — any http/https URL; the registrable hostname is resolved."
    },
    "domain": {
      "type": "string",
      "maxLength": 253,
      "description": "the domain to resolve (e.g. example.com). A full URL is also accepted; its hostname is used."
    }
  },
  "additionalProperties": false
}
    arguments 16 lines
  • readability unknown never probed

    URL → a clean ARTICLE record { title, byline, publishedAt, article text } with boilerplate (nav/header/footer/sidebar/ads/share-bars/comment-forms) stripped via deterministic DOM density heuristics, plus a signed provenance receipt pinning the cleaned article to its source — the clean-citation primitive distinct from raw markdown. Deterministic (no LLM): same URL + same source bytes ⇒ byte-identical output. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the article page to extract (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • redirect unknown never probed

    URL → a SIGNED redirect/canonical resolution: the full hop chain [{url,status}] from the link you have to where it ACTUALLY lands, the final resolved URL + status, the page's <link rel=canonical>, hop count, cross-origin flag and distinct origins traversed (affiliate-cloak / link-safety signal). Deterministic — same redirects ⇒ byte-identical resolution; no LLM. Follows HTTP 3xx only (no JS/meta-refresh execution — meta-refresh target surfaced un-followed). Receipt = EIP-191 over the resolved chain. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the link/URL to resolve (http/https) — e.g. a shortlink or affiliate URL"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • availability unknown never probed

    URL → a signed uptime/status probe: up/down, HTTP status + class, reachability reason, final URL after redirects, and a measured responseMs — wrapped in an offline-verifiable provenance receipt that makes "it was up/down at T" provable SLA evidence. Deterministic verdict (responseMs is telemetry, not signed). Keyless, no LLM, no signup. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the endpoint/page to probe for availability (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • extract unknown never probed

    TYPED structured extract for autonomous agents — URL + schema → a clean, type-safe JSON record. Where /buy/fetch returns page TEXT (and ?extract= returns string-only fields), THIS returns the schema-conformant object an LLM/RAG/trading pipeline actually consumes: pass ?url=…&schema=title,price:number,rating:number,inStock:boolean and get back { title:"…", price:19.99, rating:4.5, inStock:true } — numbers as numbers, booleans as booleans, absent fields null (honest). `schema` accepts the URL-friendly compact form (field[:type], type in string|number|integer|boolean) OR a Firecrawl/OpenAI-style JSON-Schema object ({"properties":{"price":{"type":"number"}}}). That is Firecrawl's paid 'JSON mode' headline guarantee — type-safety, 'numbers as numbers not strings' — done DETERMINISTICALLY from the page's own JSON-LD/OpenGraph/meta/microdata: keyless, NO LLM call, NO API key, NO signup, $0.004/call, paid in-band over HTTP 402 (x402, USDC on Base mainnet). The typed record is folded into the SIGNED provenance attestation too (EIP-191, ecrecoverable OFFLINE), so a buyer can prove the EXTRACTED FIELDS — not just raw bytes — are exactly what MERCURY resolved. Honest charge-per-ATTEMPT: every call returns a structured result (success OR an ok:false reason). Same SSRF guard, 5s timeout, 10MB cap, no mint. — $0.004/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url",
    "schema"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to extract from (http/https)"
    },
    "format": {
      "enum": [
        "text",
        "markdown"
      ],
      "type": "string",
      "description": "optional: text (default) or markdown for the page-text field"
    },
    "schema": {
      "type": "string",
      "maxLength": 1024,
      "description": "fields to extract. COMPACT: comma list of field[:type] (type in string|number|integer|boolean, default string), e.g. title,price:number,rating:number,inStock:boolean. OR a JSON-Schema string ({\"properties\":{\"price\":{\"type\":\"number\"}}}). Resolved from JSON-LD/OpenGraph/meta/microdata."
    }
  },
  "additionalProperties": false
}
    arguments 28 lines
  • metadata unknown never probed

    URL → one typed, SIGNED metadata record (JSON-LD + OpenGraph + Twitter-card + standard <meta> + canonical + title), by source. Deterministic, keyless, no LLM — the social-card/SEO/schema.org record an agent can PROVE. — $0.006/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the page to read metadata from (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • robots unknown never probed

    Domain → signed, timestamped per-AI-crawler allow/block audit from robots.txt + llms.txt + ai.txt (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bytespider, …). Deterministic, no LLM. EU-AI-Act / TDM opt-out evidence: the signed verdict proves the crawler policy as it stood at fetch time. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "domain"
  ],
  "properties": {
    "path": {
      "type": "string",
      "maxLength": 1024,
      "description": "optional path to evaluate the verdict for (default '/', the whole-site question)"
    },
    "domain": {
      "type": "string",
      "maxLength": 2048,
      "description": "domain or URL to audit (e.g. example.com or https://example.com/page); only the origin is used"
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • notarize unknown never probed

    Notarize any content (inline ?content= or a fetched ?url=) into a signed, offline-verifiable provenance receipt — sha256 contentHash + witnessed timestamp, attested by Mercury's pinned key. Deterministic, keyless, no LLM. The signed receipt is the product: it witnesses that these exact bytes existed in this exact form at this time (the one thing your own sha256() can't — a third-party witness). — $0.008/call

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "a page (http/https) to fetch + notarize its cleaned text. Provide EITHER url OR content, not both."
    },
    "content": {
      "type": "string",
      "maxLength": 262144,
      "description": "inline content (UTF-8, ≤256KB) to notarize directly — bytes you already hold. Provide EITHER url OR content, not both."
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • feed unknown never probed

    RSS/Atom feed URL → a SIGNED, normalized item list [{title,link,published,summary}] unified across RSS 2.0/RDF + Atom 1.0: CDATA unwrapped, HTML stripped, entities decoded, dates → ISO-8601 (publishedRaw kept verbatim, never fabricated). Deterministic — same feed bytes ⇒ byte-identical items; no LLM. Core 4 fields only (not full-content/media/author). Receipt = EIP-191 over the canonical item list. — $0.005/call

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "the RSS/Atom feed to normalize (http/https)"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your agent card — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id ea575f91f781c998.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/ea575f91f781c998/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/ea575f91f781c998/badge.svg)](https://brick.blue/agent/ea575f91f781c998?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the a2a door
card completeness
90%

How much of the published card is filled in. Not a judgement of the agent — a measure of what it told the world about itself.

spec deviations
0

Places where the published card departs from the specification. Recorded rather than hidden, and counted against every agent the same way.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.