MCP MeasureMCP Measure

índice observado

agent-media-toolkit

15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
89%
Integridad del esquema
78%
Calidad de los nombres
84%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Hallazgos (4)

  • LOWTool 'moderate' description lacks action verben moderate
  • LOWTool 'package_post' description lacks action verben package_post
  • LOWTool 'transcribe' description lacks action verben transcribe
  • LOWTool 'subtitles' description lacks action verben subtitles

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

Costo de contexto

~1,291Tokens (definiciones de herramientas)
~689 BTamaño de respuesta típico
Impacto moderado en la atención (1.01% 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": {
    "agent-media-toolkit": {
      "url": "https://podcast-shorts-a2a-production.up.railway.app/mcp/"
    }
  }
}

Puntos de conexión remotos

https://podcast-shorts-a2a-production.up.railway.app/mcp/streamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (15)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢search(query, max_results)

Live web search. Returns results with title, url, and snippet.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 5,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "searchArguments"
}
⚪news(query, max_results)

Recent news for a query/niche. Returns items with title, url, snippet, date, source.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "max_results": {
      "default": 6,
      "title": "Max Results",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "newsArguments"
}
🟢extract(url, max_chars)

Fetch a web page and return clean main-content text (no nav/ads/boilerplate).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "title": "Url",
      "type": "string"
    },
    "max_chars": {
      "default": 20000,
      "title": "Max Chars",
      "type": "integer"
    }
  },
  "required": [
    "url"
  ],
  "title": "extractArguments"
}
⚪summarize(text, url, style, max_words)

Summarize text OR a web page (give text or url). style: paragraph|bullets.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "text": {
      "default": "",
      "title": "Text",
      "type": "string"
    },
    "url": {
      "default": "",
      "title": "Url",
      "type": "string"
    },
    "style": {
      "default": "paragraph",
      "title": "Style",
      "type": "string"
    },
    "max_words": {
      "default": 120,
      "title": "Max Words",
      "type": "integer"
    }
  },
  "title": "summarizeArguments"
}
⚪repurpose(text, formats, niche)

Turn text into social assets: thread, summary, titles, hashtags.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "text": {
      "title": "Text",
      "type": "string"
    },
    "formats": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Formats"
    },
    "niche": {
      "default": "",
      "title": "Niche",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "repurposeArguments"
}
⚪translate(text, target_lang, source_lang)

Translate text into target_lang (e.g. 'Spanish', 'ja').

Esquema de entrada

{
  "type": "object",
  "properties": {
    "text": {
      "title": "Text",
      "type": "string"
    },
    "target_lang": {
      "title": "Target Lang",
      "type": "string"
    },
    "source_lang": {
      "default": "",
      "title": "Source Lang",
      "type": "string"
    }
  },
  "required": [
    "text",
    "target_lang"
  ],
  "title": "translateArguments"
}
🟡script(topic, platform, duration_s, tone)

Write a short-form video script (hook, beats, cta) for a topic.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "topic": {
      "title": "Topic",
      "type": "string"
    },
    "platform": {
      "default": "shorts",
      "title": "Platform",
      "type": "string"
    },
    "duration_s": {
      "default": 45,
      "title": "Duration S",
      "type": "integer"
    },
    "tone": {
      "default": "",
      "title": "Tone",
      "type": "string"
    }
  },
  "required": [
    "topic"
  ],
  "title": "scriptArguments"
}
⚪moderate(text)

Content-safety classification: flagged?, categories, severity, reason.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "text": {
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "moderateArguments"
}
⚪media_info(url)

Metadata (title, duration, uploader, views) for a media URL — no download.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "title": "Url",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "title": "media_infoArguments"
}
🟢voiceover(text, voice, rate)

Text -> natural MP3 narration. Returns a download URL.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "text": {
      "title": "Text",
      "type": "string"
    },
    "voice": {
      "default": "en-US-ChristopherNeural",
      "title": "Voice",
      "type": "string"
    },
    "rate": {
      "default": "+0%",
      "title": "Rate",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "voiceoverArguments"
}
🟡package_post(transcript_excerpt, platforms, niche)

Platform-optimized title, description, and hashtags for a clip. Premium (via x402).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "transcript_excerpt": {
      "title": "Transcript Excerpt",
      "type": "string"
    },
    "platforms": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Platforms"
    },
    "niche": {
      "default": "",
      "title": "Niche",
      "type": "string"
    }
  },
  "required": [
    "transcript_excerpt"
  ],
  "title": "package_postArguments"
}
⚪transcribe(source_url)

Transcribe an audio/video URL to timestamped text. Premium (via x402).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "source_url": {
      "title": "Source Url",
      "type": "string"
    }
  },
  "required": [
    "source_url"
  ],
  "title": "transcribeArguments"
}
⚪subtitles(source_url, format)

Audio/video URL -> .srt/.vtt subtitle file. Premium (via x402).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "source_url": {
      "title": "Source Url",
      "type": "string"
    },
    "format": {
      "default": "srt",
      "title": "Format",
      "type": "string"
    }
  },
  "required": [
    "source_url"
  ],
  "title": "subtitlesArguments"
}
🟢find_clips(source_url, max_clips, niche)

Find viral clip candidates in a long video with scores. Premium (via x402).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "source_url": {
      "title": "Source Url",
      "type": "string"
    },
    "max_clips": {
      "default": 5,
      "title": "Max Clips",
      "type": "integer"
    },
    "niche": {
      "default": "",
      "title": "Niche",
      "type": "string"
    }
  },
  "required": [
    "source_url"
  ],
  "title": "find_clipsArguments"
}
🟡edit_clip(source_url, start_s, end_s, style)

Cut a time range into a finished 9:16 captioned short. Premium (via x402).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "source_url": {
      "title": "Source Url",
      "type": "string"
    },
    "start_s": {
      "title": "Start S",
      "type": "number"
    },
    "end_s": {
      "title": "End S",
      "type": "number"
    },
    "style": {
      "default": "bold-captions",
      "title": "Style",
      "type": "string"
    }
  },
  "required": [
    "source_url",
    "start_s",
    "end_s"
  ],
  "title": "edit_clipArguments"
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada15 herramientas
verificadoversión no registrada15 herramientas
verificadoversión no registrada15 herramientas