webfetch
Registry code: 0012b1a4df4b772b
Fetch a URL and get back HTML, text, markdown, or JSON extracted with CSS or XPath selectors, or search Google, Bing, Yahoo and Brave with search_web (10 credits a page; needs the robots.txt opt-out on for the key: paid plans turn it on, free accounts request it). Calls are metered in credits: 1 without JavaScript rendering, 5 with it. A failed call costs nothing. An API key is REQUIRED: send it as Authorization: Bearer wfk_... on the HTTP request carrying this JSON-RPC call. A free key (1,000 credits to start, 250 more every month) is available at https://webfetch.io/signup.
- endpoint
- https://webfetch.io/mcp
- 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 webfetch live?
- Yes — it answered the hub's last check (checked 9h ago). It answered 100% of checks over the last 30 days.
- Is webfetch free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does webfetch have?
- 3 tools: extract_data, fetch_page, search_web.
- Is webfetch 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.
90 days 100%· all time 100%
last good check
of 3 tools
- unknown → live
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.
through this hub
successful
what callers paid
Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run
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.
extract_data unknown 9h ago
Fetch a URL and return JSON built from CSS or XPath selectors, so the model receives structured fields instead of a whole page.
{ "type": "object", "required": [ "url", "extract_rules" ], "properties": { "url": { "type": "string", "description": "The absolute http or https URL to fetch." }, "render_js": { "type": "boolean", "default": true, "description": "Render in a browser before extracting." }, "extract_rules": { "type": "object", "description": "Map a name to a selector. A string is shorthand for the text of the first match, and \"a@href\" takes an attribute. An object may set selector, selector_type (auto, css, xpath), type (item or list), and output (text, html, @attr, table_json, table_array, or a nested object of further rules). Example: {\"titles\": {\"selector\": \"h2\", \"type\": \"list\"}}" } } }arguments 22 linesfetch_page unknown 9h ago
Fetch a URL and return its content as markdown, plain text or raw HTML. JavaScript is rendered by default, which costs 5 credits; set render_js to false for a plain HTTP fetch at 1 credit. A failed fetch costs nothing.
{ "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "description": "The absolute http or https URL to fetch." }, "render_js": { "type": "boolean", "default": true, "description": "Render in a browser. False is cheaper and faster but misses anything drawn by JavaScript." }, "return_format": { "enum": [ "markdown", "text", "html" ], "type": "string", "default": "markdown", "description": "markdown and text strip the page chrome and are what a model usually wants. html returns the document unchanged." } } }arguments 27 linessearch_web unknown 9h ago
Run a search on Google, Bing, Yahoo and Brave and return one page of ranked results as JSON: organic results with title, URL and snippet, the ads, related searches and questions. 10 credits per page (15 with light_request false). Needs the robots.txt opt-out turned on for the key: paid plans turn it on in the key portal, and free accounts request search access there. A failed search costs nothing.
{ "type": "object", "required": [ "query" ], "properties": { "page": { "type": "integer", "default": 1, "maximum": 50, "minimum": 1, "description": "Results page." }, "query": { "type": "string", "description": "What to search for, as typed in the search box." }, "engine": { "enum": [ "google", "bing", "yahoo", "brave" ], "type": "string", "default": "google", "description": "The search engine." }, "search_type": { "enum": [ "classic", "ads" ], "type": "string", "default": "classic", "description": "classic for the full page, ads for the ads only." }, "country_code": { "type": "string", "default": "us", "description": "Two-letter country to search from." }, "light_request": { "type": "boolean", "default": true, "description": "False loads the page in a browser, which on Bing includes the ads, at 15 credits." } } }arguments 49 lines
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.
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.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id0012b1a4df4b772b.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/0012b1a4df4b772b/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/0012b1a4df4b772b?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.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 1
- ok
- 0
- failed
- 1
- success rate
- 0%
- median latency
- 568ms
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
1 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.