A real browser for your agent: any page, or 25 pages of a site, to clean text. $1 per call via x402.
Scored across 2 tools
The two tools have clearly distinct scopes: one extracts a single page and one extracts an entire site section. There is no meaningful overlap or ambiguity between them.
Both tools follow the exact same `<target>_extract` pattern, making the naming predictable and internally consistent. The style is uniform across the whole server.
Two tools is lean, but it is reasonable for the server's focused purpose of web text extraction. A single-page tool and a batch site-extraction tool cover the core need without unnecessary duplication.
The server covers both individual page extraction and multi-page site extraction, including crawl planning and bot-wall handling. Minor gaps exist, such as no way to extract more than 25 pages or explicitly select specific URLs, but these are edge cases rather than core gaps.
Render any public web page in a real headless Chrome and return its text. JavaScript runs first, so docs sites and single-page apps that a plain fetch returns empty come back complete. $1 per call (x402 on Arc/Base/Solana/X1): the full text and every outbound link. Without a payment the call returns the price and every rail we accept. Refuses private and reserved addresses and our own hosts, so it cannot be used as a proxy into a network. Sites that put a bot wall in front of their pages (Cloudflare, DataDome and the like) answer with a challenge rather than the page: the call then FAILS with http-403 or bot-challenge and says so, rather than charging you for a spinner.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | the http(s) page to render | |
| full | No | true asks for the paid full text. Without a payment you get a 402 carrying the price and every rail we accept; sign it and call again with `payment`. | |
| payment | No | a signed x402 payment (the same base64 payload you would put in the PAYMENT-SIGNATURE header). Pass it here and the purchase completes inside this tool call - you never have to leave MCP. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and delivers thoroughly: it discloses the $1-per-call pricing, the 402-with-rails behavior when unpaid, the payment-completes-inside-call flow, SSRF protections, and the exact failure modes (http-403/bot-challenge) with an assurance the caller isn't charged for a spinner. Exceptionally transparent for a paid mutation-style tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Longer than average, but every sentence earns its place given the tool's complexity (pricing, payment flow, security constraints, failure modes). The core purpose is front-loaded and the length is justified, though it could be tightened without losing substance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a paid tool with a payment flow and no output schema, the description covers rendering behavior, pricing, payment mechanics, SSRF refusal, and bot-wall failures. The only gap is the return format of the 'full text' and links payload, which would help an agent parse results, but overall it is highly complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema: it explains the end-to-end payment lifecycle (get a 402 with price and rails, sign it, pass the payload via `payment` to complete inside the call) and clarifies that `full` buys full text plus every outbound link. This enriches the terse schema wording.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Render any public web page in a real headless Chrome and return its text'). Distinguishes behaviorally from a plain fetch and the likely sibling site_extract by noting JavaScript runs first so docs sites and SPAs come back complete. The purpose is unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear context for when the tool shines (JS-heavy docs sites, single-page apps that a plain fetch returns empty) and notes capability limits (refuses private/reserved addresses, can't proxy into a network, bot walls fail). Stops short of explicitly naming an alternative tool for simple static pages or a when-not-to-use routing, so it earns 4 rather than 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render a whole section of a site - up to 25 pages - in one call and get every page back as clean text, with JavaScript executed. Same host only; robots.txt is obeyed and anything it disallows is skipped and named. FREE: the crawl PLAN - exactly which pages would be fetched and what robots.txt allows - so you can see what you would get before paying. PAID ($1.00, x402 on Arc/Base/Solana/X1): every page rendered and returned. Priced at a dollar because it is up to 25 real browser renders, not a lookup. If a bot wall on the site lets the first page through but blocks the rest, the call fails with poor-yield and names every page it could not render, instead of billing a dollar for a list of failures.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | the page to start from | |
| full | No | true asks for the paid crawl. Without a payment you get a 402 carrying the price and every rail we accept; sign it and call again with `payment`. | |
| pages | No | how many pages, default 10, hard cap 25 | |
| payment | No | a signed x402 payment (the same base64 payload you would put in the PAYMENT-SIGNATURE header). Pass it here and the purchase completes inside this tool call. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it delivers extensively: JavaScript execution, same-host restriction, robots.txt compliance with skipped pages named, free/paid gating, the exact $1.00 price and payment rails, the 402 flow, and the poor-yield failure mode that explicitly does not bill. This is far richer behavioral disclosure than annotations would typically supply.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured: core capability first, then explicit FREE/PAID sections, then failure mode. Nearly every sentence carries operational information an agent needs. Minor deductions for the promotional clause 'Priced at a dollar because it is up to 25 real browser renders, not a lookup' and slight redundancy between the schema and prose on the payment flow.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a complex tool - payment rails, free/paid modes, crawl constraints, robots.txt, and a custom failure path - and with no output schema, the description must explain return values, which it does: the crawl plan for free calls, rendered clean text for paid calls, and the named-page poor-yield error. Nothing an agent needs to call it correctly and set expectations is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: it explains the `full` flag's 402/price flow, elaborates that `payment` is a previously signed x402 payload to resubmit, and frames `pages` within the 25-page hard cap and per-render cost rationale. The schema says 'sign it and call again' but the description clarifies the failure and non-billing semantics around it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Render a whole section of a site - up to 25 pages - in one call and get every page back as clean text, with JavaScript executed.' The multi-page crawl scope clearly separates it from the sibling page_extract (single-page) tool, and the 'whole section of a site' phrasing makes the tool's distinguishing purpose obvious without needing to inspect either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives strong decision context: when to use the FREE crawl plan vs the PAID render, the full payment flow (402 with rails, sign, resubmit with `payment`), the same-host constraint, and the poor-yield failure behavior with no billing. It does not explicitly name an alternative for single-page extraction or state a when-not condition, so it falls just short of the explicit-exclusion bar.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
page_extractsite_extractA real browser for your agent: render any page, or 25 pages of a site, to clean text.
Turn any URL into clean, structured, agent-ready content. $0.02/call via x402 on Base.
AI web extraction: send URLs + a JSON Schema, get clean structured data. Pay-per-use via x402.
Pay-per-call browser rendering and x402 marketplace ranking for AI agents, billed via USDC.
Add one secure layer between your agents and this server.