Find documented page-extraction services. Free experiment; optional telemetry; no provider calls.
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.
Find page_extraction alternatives; structured format, JavaScript, auth and price constraints only. No URL/task prompt. Consent defaults off.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http machine-demand-radar-finder https://idea3bkqh5soidx2afk2k26udm0bdfyv.lambda-url.eu-central-1.on.aws/mcp
Find page_extraction alternatives; structured format, JavaScript, auth and price constraints only. No URL/task prompt. Consent defaults off.
| Argument | Type | Description |
|---|---|---|
| request* | any |
{
"type": "object",
"$defs": {
"Request": {
"type": "object",
"title": "Request",
"required": [
"capabilities"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 5,
"maximum": 10,
"minimum": 1
},
"origin": {
"enum": [
"owner_test",
"synthetic",
"health_check",
"self_declared_external",
"unknown"
],
"type": "string",
"title": "Origin",
"default": "unknown"
},
"billing_unit": {
"anyOf": [
{
"enum": [
"page",
"token",
"session"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Billing Unit",
"default": null
},
"capabilities": {
"type": "array",
"items": {
"enum": [
"page_extraction",
"web_search",
"browser_automation"
],
"type": "string"
},
"title": "Capabilities",
"maxItems": 3,
"minItems": 1
},
"max_price_usd": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Max Price Usd",
"default": null
},
"output_format": {
"anyOf": [
{
"enum": [
"markdown",
"text",
"html",
"json"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Output Format",
"default": null
},
"authentication": {
"enum": [
"any",
"none",
"api_key"
],
"type": "string",
"title": "Authentication",
"default": "any"
},
"idempotency_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Idempotency Key",
"default": null
},
"task_session_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Task Session Id",
"default": null
},
"telemetry_consent": {
"type": "boolean",
"title": "Telemetry Consent",
"default": false
},
"installation_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Installation Token",
"default": null
},
"javascript_required": {
"type": "boolean",
"title": "Javascript Required",
"default": false
}
},
"additionalProperties": false
}
},
"title": "find_agent_servicesArguments",
"required": [
"request"
],
"properties": {
"request": {
"$ref": "#/$defs/Request"
}
}
}Report selected_service, caller_declared_completion/failure or not_useful with a consented search_id; structured rejection_reason only.
| Argument | Type | Description |
|---|---|---|
| request* | any |
{
"type": "object",
"$defs": {
"Outcome": {
"type": "object",
"title": "Outcome",
"required": [
"search_id",
"event_type"
],
"properties": {
"result_id": {
"anyOf": [
{
"type": "string",
"maxLength": 80
},
{
"type": "null"
}
],
"title": "Result Id",
"default": null
},
"search_id": {
"type": "string",
"title": "Search Id",
"maxLength": 128,
"minLength": 16
},
"event_type": {
"enum": [
"selected_service",
"caller_declared_completion",
"caller_declared_failure",
"not_useful"
],
"type": "string",
"title": "Event Type"
},
"rejection_reason": {
"anyOf": [
{
"enum": [
"incompatible_format",
"rendering_requirement",
"authentication_friction",
"price",
"unknown_capability",
"provider_failure"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Rejection Reason",
"default": null
}
},
"additionalProperties": false
}
},
"title": "record_finder_outcomeArguments",
"required": [
"request"
],
"properties": {
"request": {
"$ref": "#/$defs/Outcome"
}
}
}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 4, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.