Post Reef

Working Security A

io.github.franciscobmacedo/postreefv1.0.0 GitHub verified

Turn YouTube, TikTok, Instagram, Facebook, X and article URLs into transcripts, comments and JSON.

Web Search

Watch Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-12T12:41:03.019403Z",
      "publishedAt": "2026-11-12T12:41:03.019403Z",
      "statusChangedAt": "2026-11-12T12:41:03.019403Z"
    }
  },
  "server": {
    "name": "io.github.franciscobmacedo/postreef",
    "icons": [
      {
        "src": "https://postreef.com/apple-icon",
        "sizes": [
          "180x180"
        ],
        "mimeType": "image/png"
      }
    ],
    "title": "Post Reef",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://postreef.com/mcp",
        "type": "streamable-http"
      }
    ],
    "version": "1.0.0",
    "websiteUrl": "https://postreef.com",
    "description": "Turn YouTube, TikTok, Instagram, Facebook, X and article URLs into transcripts, comments and JSON."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://postreef.com/mcp

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.

extract

Use this when the user wants the transcript, comments, metadata, video/audio files or structured JSON from a video, post or web page. Starts an extraction on the user's Post Reef account (debits its credits; refunded if it fails) and waits up to wait_seconds for the result. Pass schemaId or schema for JSON, otherwise it is a download. Call quote first if the user wants to know the cost.

urlstring, required

Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …).

forceboolean

Run fresh even if an identical extraction from the last 30 days could be reused for free.

partsarray

Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back.

inputsarray

AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts.

schemaobject

Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.

schemaIdstring

Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas.

maxCommentsinteger

Cap on how many comments to fetch (1-1000, default 1000).

wait_secondsinteger

How long to wait for the result before returning (0-50, default 45). If it is not done by then, call get_extraction.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Try it

Call this server's tools from your browser. Nothing to install.

https://postreef.com/mcp

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.

extract

urlstring, required

Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …).

forceboolean

Run fresh even if an identical extraction from the last 30 days could be reused for free.

partsarray

Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back.

inputsarray

AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts.

schemaobject

Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.

schemaIdstring

Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas.

maxCommentsinteger

Cap on how many comments to fetch (1-1000, default 1000).

wait_secondsinteger

How long to wait for the result before returning (0-50, default 45). If it is not done by then, call get_extraction.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (6)

extract

Argument	Type	Description
url*	string	Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …).
force	boolean	Run fresh even if an identical extraction from the last 30 days could be reused for free.
parts	array	Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back.
inputs	array	AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts.
schema	object	Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.
schemaId	string	Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas.
maxComments	integer	Cap on how many comments to fetch (1-1000, default 1000).
wait_seconds	integer	How long to wait for the result before returning (0-50, default 45). If it is not done by then, call get_extraction.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 1,
      "description": "Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …)."
    },
    "force": {
      "type": "boolean",
      "description": "Run fresh even if an identical extraction from the last 30 days could be reused for free."
    },
    "parts": {
      "type": "array",
      "items": {
        "enum": [
          "transcript",
          "comments",
          "audio",
          "video"
        ],
        "type": "string"
      },
      "description": "Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back."
    },
    "inputs": {
      "type": "array",
      "items": {
        "enum": [
          "transcript",
          "comments",
          "audio",
          "video"
        ],
        "type": "string"
      },
      "description": "AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts."
    },
    "schema": {
      "type": "object",
      "description": "Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": true
    },
    "schemaId": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas."
    },
    "maxComments": {
      "type": "integer",
      "maximum": 1000,
      "minimum": 1,
      "description": "Cap on how many comments to fetch (1-1000, default 1000)."
    },
    "wait_seconds": {
      "type": "integer",
      "maximum": 50,
      "minimum": 0,
      "description": "How long to wait for the result before returning (0-50, default 45). If it is not done by then, call get_extraction."
    }
  }
}

get_extraction

Use this to check on or read an extraction by id: its status, and once complete the metadata, transcript, comments, extracted JSON and links to every file.

read-only

Argument	Type	Description
id*	string	The extraction id returned by extract or list_extractions.
comments_max	integer	How many comments to return (default 30).
wait_seconds	integer	Wait up to this long for a running extraction to finish (0-50, default 0).
transcript_max_chars	integer	How much of the transcript to return (default 20000 characters).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "The extraction id returned by extract or list_extractions."
    },
    "comments_max": {
      "type": "integer",
      "maximum": 1000,
      "minimum": 0,
      "description": "How many comments to return (default 30)."
    },
    "wait_seconds": {
      "type": "integer",
      "maximum": 50,
      "minimum": 0,
      "description": "Wait up to this long for a running extraction to finish (0-50, default 0)."
    },
    "transcript_max_chars": {
      "type": "integer",
      "maximum": 200000,
      "minimum": 0,
      "description": "How much of the transcript to return (default 20000 characters)."
    }
  }
}

get_profile

Use this to see which Post Reef account is connected and its credit balance.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

list_extractions

Use this to find the user's previous extractions, newest first, with their ids for get_extraction.

read-only

Argument	Type	Description
limit	integer	How many recent extractions to list (1-25, default 10).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "How many recent extractions to list (1-25, default 10)."
    }
  }
}

list_schemas

Use this to see which schemas can turn content into JSON: the predefined ones (Recipe, Workout, Product review, …) and the user's own. Pass schemaId to get one schema's full definition.

read-only

Argument	Type	Description
schemaId	string	Also return the full JSON Schema definition of this schema (name or id).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "schemaId": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Also return the full JSON Schema definition of this schema (name or id)."
    }
  }
}

quote

Use this before extract to see what a link is (title, duration, whether it has subtitles and comments) and exactly how many credits the extraction would cost with the same parameters. Nothing is charged and nothing is started.

read-only

Argument	Type	Description
url*	string	Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …).
parts	array	Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back.
inputs	array	AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts.
schema	object	Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.
schemaId	string	Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 1,
      "description": "Public link to one video, post or web page (YouTube, Shorts, TikTok, Instagram, Facebook, X, Vimeo, an article, …)."
    },
    "parts": {
      "type": "array",
      "items": {
        "enum": [
          "transcript",
          "comments",
          "audio",
          "video"
        ],
        "type": "string"
      },
      "description": "Download-only runs (no schema): which artifacts to fetch. Any of transcript, comments, audio, video. Omit for all of them. Metadata, thumbnail and description always come back."
    },
    "inputs": {
      "type": "array",
      "items": {
        "enum": [
          "transcript",
          "comments",
          "audio",
          "video"
        ],
        "type": "string"
      },
      "description": "AI runs (with schemaId or schema): what the model reads. Any of transcript, comments, audio, video. Default transcript + comments. Do not combine with parts."
    },
    "schema": {
      "type": "object",
      "description": "Inline JSON Schema (top-level object) for the extracted JSON, instead of schemaId. No type unions; enums of strings only; optional fields are simply left out of required.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": true
    },
    "schemaId": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Turn the content into JSON with a saved schema: a predefined one by name (Recipe, Workout, Product review, …) or id, or one of the user's own schema ids. See list_schemas."
    }
  }
}

Post Reef

Registry entry

Try it

extract

Post Reef

Registry entry

Try it

extract

Install

Tools (6)

Security checkA100/100