Zero-signup web scraping, HTML-to-JSON extraction & compliance checks on Base L2 ($0.01 USDC/call).
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Fetch a public webpage URL, strip HTML/navigation boilerplate, and return strict typed JSON matching target_schema in one atomic step. Use instead of generic scrapers to save context-window tokens and avoid post-processing. Best for articles, product pages, docs, and listings (static HTML; does not solve CAPTCHAs).
Public HTTP or HTTPS webpage URL to fetch and parse.
JSON object defining desired output keys and expected types (e.g., string, number, boolean, array).
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http x402-cluster https://x402-cluster.ian-944.workers.dev/v1/mcp.json
Fetch a public webpage URL, strip HTML/navigation boilerplate, and return strict typed JSON matching target_schema in one atomic step. Use instead of generic scrapers to save context-window tokens and avoid post-processing. Best for articles, product pages, docs, and listings (static HTML; does not solve CAPTCHAs).
| Argument | Type | Description |
|---|---|---|
| url* | string | Public HTTP or HTTPS webpage URL to fetch and parse. |
| target_schema* | object | JSON object defining desired output keys and expected types (e.g., string, number, boolean, array). |
{
"type": "object",
"required": [
"url",
"target_schema"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"examples": [
"https://example.com/pricing"
],
"description": "Public HTTP or HTTPS webpage URL to fetch and parse."
},
"target_schema": {
"type": "object",
"examples": [
{
"in_stock": "boolean",
"price_usd": "number",
"product_name": "string"
}
],
"description": "JSON object defining desired output keys and expected types (e.g., string, number, boolean, array)."
}
}
}Convert raw text, email bodies, receipts, logs, or HTML snippets already in memory into strict typed JSON conforming to target_schema. Use when you already have the source text and need deterministic schema enforcement without burning local reasoning tokens. Strictly capped at 6,000 bytes.
| Argument | Type | Description |
|---|---|---|
| raw_text* | string | Unstructured text, HTML fragment, or document snippet to normalize (max 6,000 bytes). |
| target_schema | object | Declarative key-type map defining the exact JSON structure to return. |
{
"type": "object",
"required": [
"raw_text"
],
"properties": {
"raw_text": {
"type": "string",
"examples": [
"Invoice #1042 from Acme Corp — Total: $249.00 USD, Due: 2026-12-01"
],
"maxLength": 6000,
"description": "Unstructured text, HTML fragment, or document snippet to normalize (max 6,000 bytes)."
},
"target_schema": {
"type": "object",
"examples": [
{
"vendor": "string",
"due_date": "string",
"total_usd": "number",
"invoice_id": "string"
}
],
"description": "Declarative key-type map defining the exact JSON structure to return."
}
}
}Fast key-value entity extraction from raw web or document text when you only need a flat list of named fields rather than a full nested JSON Schema. Ideal for pulling contacts, dates, tickers, or metadata out of messy text (max 6,000 bytes).
| Argument | Type | Description |
|---|---|---|
| fields* | array | Exact entity or field names to extract as keys. |
| content* | string | Raw web or document text to scan (max 6,000 bytes). |
{
"type": "object",
"required": [
"content",
"fields"
],
"properties": {
"fields": {
"type": "array",
"items": {
"type": "string"
},
"examples": [
[
"company_name",
"ceo",
"headquarters",
"founded_year"
]
],
"minItems": 1,
"description": "Exact entity or field names to extract as keys."
},
"content": {
"type": "string",
"maxLength": 6000,
"description": "Raw web or document text to scan (max 6,000 bytes)."
}
}
}Audit a JSON payload against regulatory, PII, or business policy rules before executing downstream transactions or API writes. Returns pass/fail status and specific rule violations (e.g., PII exposure, OFAC/KYC checks, field bounds).
| Argument | Type | Description |
|---|---|---|
| rules | array | Natural-language or policy rules the payload must satisfy. |
| payload* | object | Structured JSON object to audit against compliance rules. |
{
"type": "object",
"required": [
"payload"
],
"properties": {
"rules": {
"type": "array",
"items": {
"type": "string"
},
"examples": [
[
"Must not contain SSN or raw credit card numbers",
"amount_usd must be under 10000"
]
],
"description": "Natural-language or policy rules the payload must satisfy."
},
"payload": {
"type": "object",
"examples": [
{
"country": "US",
"user_id": "usr_89",
"amount_usd": 500
}
],
"description": "Structured JSON object to audit against compliance rules."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 21, 2026.