Vera

Scrape, search and extract the public web. 3,000 free credits at https://vera.waggle.ae/signup

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
98%
Integridad del esquema
100%
Calidad de los nombres
83%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~2,770Tokens (definiciones de herramientas)
~2.8 KBTamaño de respuesta típico
Impacto significativo en la atención (2.16% del contexto de 128k)

Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.

Instalar

Instalación con un clic

Agrega esto a tu archivo `claude_desktop_config.json`:

{
  "mcpServers": {
    "vera": {
      "url": "https://vera.waggle.ae/v1/mcp"
    }
  }
}

Puntos de conexión remotos

https://vera.waggle.ae/v1/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (8)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢scrape(url, response_format, return_html, render, wait_ms, ...)

Read one public web page and return its content: the main text (as Markdown with response_format="markdown"), links, metadata and a quality score, plus the raw HTML if you ask (return_html). Set render=true for pages that build their content with JavaScript, or mode="auto" to render only when a plain fetch comes back empty. extract pulls named fields out with CSS selectors. Costs 1 credit for a plain fetch and 5 credits when the page is rendered; a failed call costs nothing. Pages that disallow automated access or need a login cannot be read.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The full public http(s) address of the page."
    },
    "response_format": {
      "default": "all",
      "enum": [
        "text",
        "markdown",
        "all"
      ],
      "type": "string",
      "description": "Use \"markdown\" to get the page's main content as Markdown in data.markdown, the best form for reading or summarising. \"all\" (the default) and \"text\" return the standard fields: text, links, metadata and a quality score."
    },
    "return_html": {
      "default": false,
      "type": "boolean",
      "description": "Also return the page's raw HTML in data.html (up to 2 MB). Not with extract."
    },
    "render": {
      "default": false,
      "type": "boolean",
      "description": "Run the page's JavaScript in a browser first, for pages that build their content in the browser. Costs more."
    },
    "wait_ms": {
      "default": 500,
      "maximum": 3000,
      "minimum": 0,
      "type": "integer",
      "description": "Milliseconds to wait after the page loads. Needs render=true."
    },
    "wait_for": {
      "maxLength": 200,
      "minLength": 1,
      "type": "string",
      "description": "A CSS selector to wait for before reading. Needs render=true."
    },
    "extract": {
      "additionalProperties": {
        "additionalProperties": false,
        "properties": {
          "selector": {
            "maxLength": 200,
            "minLength": 1,
            "type": "string"
          },
          "attribute": {
            "pattern": "^[A-Za-z][A-Za-z0-9_-]{0,63}$",
            "type": "string"
          },
          "multiple": {
            "default": false,
            "type": "boolean"
          }
        },
        "required": [
          "selector"
        ],
        "type": "object"
      },
      "maxProperties": 10,
      "type": "object",
      "description": "Named fields to pull out with a CSS selector, for example {\"heading\":{\"selector\":\"h1\"},\"links\":{\"selector\":\"a\",\"attribute\":\"href\", \"multiple\":true}}. One tag, class, ID or attribute selector each. Static pages only."
    },
    "mode": {
      "default": "manual",
      "enum": [
        "manual",
        "auto"
      ],
      "type": "string",
      "description": "\"manual\" (the default) does what render says. \"auto\" fetches the page plainly and renders it only when it looks empty; it holds up to max_cost credits and charges what it used."
    },
    "max_cost": {
      "maximum": 5,
      "minimum": 1,
      "type": "integer",
      "description": "With mode=auto, the most to spend: 1 never renders, 5 may render."
    },
    "min_quality_score": {
      "maximum": 100,
      "minimum": 0,
      "type": "integer",
      "description": "Refuse the page, at no charge, when its quality score is below this."
    },
    "country": {
      "pattern": "^[a-zA-Z]{2}$",
      "type": "string",
      "description": "Two-letter country code for the language headers of the request, for example ae or gb. It does not route the request through that country."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢search(query, vertical, country, language, limit, ...)

Search Google and return the results: titles, URLs and snippets, plus Google's own answer boxes, People Also Ask and related searches when it shows them. vertical picks web (the default), news or videos. Returns up to 100 results per call (10 by default), with country and language. Costs 3 credits per call whatever the vertical or limit; a failed search costs nothing. Results are links and snippets: use scrape to read a page.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "query": {
      "maxLength": 500,
      "minLength": 1,
      "type": "string",
      "description": "What to search for. Quoted phrases and site: operators are kept."
    },
    "vertical": {
      "type": "string",
      "enum": [
        "web",
        "news",
        "videos"
      ],
      "default": "web",
      "description": "\"web\" (the default), \"news\" or \"videos\"."
    },
    "country": {
      "default": "us",
      "pattern": "^[a-z]{2}$",
      "type": "string",
      "description": "Two lowercase letters for the search market, for example us, gb or ae (default \"us\")."
    },
    "language": {
      "default": "en",
      "pattern": "^[a-z]{2}$",
      "type": "string",
      "description": "Two lowercase letters for the result language, for example en or ar (default \"en\")."
    },
    "limit": {
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "type": "integer",
      "description": "How many results to return (10 by default). The price is the same whatever the number."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢extract_contacts(url, idempotency_key)

Read one public page and return the contact details it publishes: email addresses, phone numbers, social profile links and links to contact pages, each with where it was found. Published details are not verified, and linked pages are not followed (call this tool again for one). Costs 1 credit; a failed call costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The full public http(s) address of the page."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢extract_products(url, marketplace, idempotency_key)

Read one public product page and return the product data it publishes in its structured markup: name, brand, SKU or GTIN, and offers with price, currency and availability. Prices are what the page states, never guessed. Set marketplace to amazon, walmart or shopee for those product pages. Costs 1 credit; a failed call costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The full public http(s) address of the product page."
    },
    "marketplace": {
      "enum": [
        "amazon",
        "walmart",
        "shopee"
      ],
      "type": "string",
      "description": "Set to \"amazon\", \"walmart\" or \"shopee\" for a product page on that marketplace."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢youtube_transcript(url, idempotency_key)

Return the transcript of one public YouTube video as text. Costs 6 credits per started minute of video (a 10-minute video costs 60), up to 45 minutes. A video that cannot be transcribed, or any failure, costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The link of a public YouTube video, like https://www.youtube.com/watch?v=..."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢company_profile(domain, idempotency_key)

Given a company's domain, read its homepage and up to 3 standard pages (about, contact, team) and return a profile: name, description, logo, address, founding date, emails, phones and social links, as the company publishes them. Costs 1 credit for each page read, at most 5 credits (that many are held while it runs and the unused ones are given back); a failed call costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "domain": {
      "maxLength": 255,
      "minLength": 3,
      "type": "string",
      "description": "The company's domain or website address, for example example.com."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false
}
🟢sitemap(url, limit, filter_pattern, idempotency_key)

Read a site's sitemap.xml (or a sitemap index) and return the page addresses it lists, up to limit (100 by default), optionally only those containing some text. Costs 1 credit; a failed call costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The address of the sitemap.xml, or of a sitemap index."
    },
    "limit": {
      "default": 100,
      "maximum": 1000,
      "minimum": 1,
      "type": "integer",
      "description": "How many page addresses to return (100 by default)."
    },
    "filter_pattern": {
      "maxLength": 200,
      "type": "string",
      "description": "Keep only addresses that contain this text."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢seo_audit(url, render, country, idempotency_key)

Audit one public page's technical SEO and how ready it is for AI search: title, description, canonical, robots and indexing directives, headings, links, images, structured data and a score. Costs 1 credit, or 5 credits with render=true (audited after its JavaScript runs); a failed call costs nothing.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "maxLength": 2048,
      "minLength": 8,
      "type": "string",
      "description": "The full public http(s) address of the page."
    },
    "render": {
      "default": false,
      "type": "boolean",
      "description": "Audit the page after its JavaScript has run. Costs more."
    },
    "country": {
      "pattern": "^[a-zA-Z]{2}$",
      "type": "string",
      "description": "Two-letter country code for the language headers of the request, for example ae or gb. It does not route the request through that country."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 16,
      "maxLength": 128,
      "pattern": "^[A-Za-z0-9_.:-]+$",
      "description": "Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada8 herramientas