Rootpublish AI facts check
Check what an AI assistant tells buyers about a company against the company's own pricing pages.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"ai-facts": {
"url": "https://rootpublish.com/mcp"
}
}
}Remote-Endpunkte
https://rootpublish.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (3)
⚪buyer_questions(site, company, offer, depth)
Start an AI facts check: returns the questions a buyer asks about a company. Answer them yourself, with web search, before reading anything from the company.
Eingabe-Schema
{
"type": "object",
"properties": {
"site": {
"type": "string",
"description": "The company's site, e.g. https://example.com"
},
"company": {
"type": "string",
"description": "The company or product name buyers use"
},
"offer": {
"type": "string",
"description": "The product or service to ask about"
},
"depth": {
"type": "string",
"enum": [
"full",
"quick"
],
"description": "full asks three questions (default); quick asks one"
}
},
"required": [
"site"
]
}⚪company_statements(site, company, pages)
After you have answered the buyer questions: reads the company's pricing and service pages and returns its statements with instructions for comparing your answers.
Eingabe-Schema
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"company": {
"type": "string"
},
"pages": {
"type": "array",
"items": {
"type": "string"
},
"description": "Paths of the pages that state prices and terms, e.g. [\"/pricing\"]"
}
},
"required": [
"site"
]
}⚪verify_findings(site, pages, answer, judgement)
Keeps only the differences whose quotes are really in your answer and on the company's page, and finds the pages your answer cited that carry a wrong figure. Call once per answer.
Eingabe-Schema
{
"type": "object",
"properties": {
"site": {
"type": "string"
},
"pages": {
"type": "array",
"items": {
"type": "string"
},
"description": "The pages returned by company_statements"
},
"answer": {
"type": "string",
"description": "One of your full answers, exactly as you wrote it"
},
"judgement": {
"type": "string",
"description": "Your findings for that answer as a JSON object"
}
},
"required": [
"site",
"answer",
"judgement"
]
}Community
Nachweis