Skip to main content
Glama
deenesjakoruzh
mario-andreschak

MCP Video Recognition Server

by mario-andreschak
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

MCP Video Recognition Server

Ein MCP-Server, der Bilder beschreibt, Audio transkribiert und Videos aus lokalen Dateien zusammenfasst. Er verwendet standardmäßig Google Gemini oder einen beliebigen OpenAI-kompatiblen Endpunkt wie OpenRouter.

Funktionen

  • Wählen Sie Ihren Anbieter: Google Gemini (Standard) oder einen OpenAI-kompatiblen Endpunkt

  • Drei MCP-Tools für lokale Bilder, Audio und Video

  • Optionale Gemini-Modell-Fallback plus ein letztes OpenAI-kompatibles Backup

Die Modellunterstützung variiert. Die Wahl des OpenAI-kompatiblen Anbieters bedeutet nicht, dass jeder Endpunkt oder jedes Modell jeden Medientyp verarbeitet, und der Server ersetzt für Sie niemals ein Modell oder einen Anbieter.

Related MCP server: Puter MCP Server

Voraussetzungen

  • Node.js 18.0.0 oder höher

  • Ein API-Schlüssel für Ihren Anbieter:

    • Gemini: GOOGLE_API_KEY

    • OpenAI-kompatibel: OPENAI_COMPATIBLE_API_KEY

Installation

git clone https://github.com/yourusername/mcp-video-recognition.git
cd mcp-video-recognition
npm install
npm run build

Schnellstart

Fügen Sie den Server zu Ihrer MCP-Client-Konfiguration hinzu und verweisen Sie auf das erstellte dist/index.js:

{
  "mcpServers": {
    "video-recognition": {
      "command": "node",
      "args": ["/path/to/mcp-video-recognition/dist/index.js"],
      "env": {
        "GOOGLE_API_KEY": "your_google_api_key"
      }
    }
  }
}

Unter Windows verwenden Sie Schrägstriche oder doppelte Backslashes (\\) im Pfad. Speichern Sie die Datei und verbinden Sie Ihren MCP-Client neu.

Für OpenRouter oder einen anderen OpenAI-kompatiblen Endpunkt setzen Sie RECOGNITION_PROVIDER=openai-compatible sowie dessen Variablen. Siehe Konfiguration für ein fertiges Beispiel.

Mit FLUJO:

  1. Klicken Sie auf Server hinzufügen.

  2. Fügen Sie die GitHub-URL ein.

  3. Klicken Sie auf Parsen, Klonen, Installieren, Erstellen und Speichern.

Konfiguration

Der Server liest Umgebungsvariablen. Die häufigsten sind:

Variable

Standard

Zweck

RECOGNITION_PROVIDER

gemini

gemini oder openai-compatible

GOOGLE_API_KEY

keine

Gemini-API-Schlüssel

GEMINI_MODEL

gemini-3.5-flash

Zu verwendendes Gemini-Modell

OPENAI_COMPATIBLE_API_KEY

keine

OpenAI-kompatibler API-Schlüssel

OPENAI_COMPATIBLE_BASE_URL

keine

Basis-URL des Endpunkts

OPENAI_COMPATIBLE_MODEL

xiaomi/mimo-v2.5

Zu verwendendes Modell

ALLOWED_MEDIA_ROOTS

keine

Medienverzeichnisse für den OpenAI-kompatiblen Anbieter und das Gemini-Backup

Ungültige Werte verhindern den Start; sie werden nicht stillschweigend korrigiert.

Die vollständige Variablenliste, Validierungsregeln, das OpenRouter-Beispiel und unterstützte Medientypen finden Sie in der Konfigurationsreferenz.

Für den Gemini-Modell-Fallback und das letzte Backup siehe Referenz zur Anbieter-Wiederherstellung.

Tools

Der Server stellt drei MCP-Tools bereit. Jedes nimmt einen lokalen filepath, einen optionalen prompt (Standard Describe this content) und eine optionale modelname-Überschreibung.

  • image_recognition — ein Bild beschreiben

  • audio_recognition — Audio transkribieren oder beschreiben

  • video_recognition — ein Video beschreiben

Beispiel:

{
  "name": "video_recognition",
  "arguments": {
    "filepath": "/path/to/video.mp4",
    "prompt": "Describe what happens in this video"
  }
}

Sicherheit

  • HTTPS ist standardmäßig erforderlich. Nur-Text-HTTP ist nur für einen explizit aktivierten lokalen Endpunkt erlaubt.

  • Der OpenAI-kompatible Anbieter und das Gemini-Backup lesen Medien nur aus Verzeichnissen, die Sie in ALLOWED_MEDIA_ROOTS angeben.

  • Schlüssel bleiben in der Prozessumgebung. Nehmen Sie keine echten Schlüssel in die Versionskontrolle auf.

Endpunktregeln, Ressourcengrenzen und Reaktion auf Vorfälle finden Sie in der Sicherheitsreferenz.

Entwicklung

# Run in development mode
GOOGLE_API_KEY=your_api_key npm run dev

# Build and run the provider foundation tests
npm run verify:provider-foundation

Projektstruktur

  • src/index.ts: Einstiegspunkt und Anbieterkonstruktion

  • src/server.ts: MCP-Server und Transport

  • src/tools/: die drei Erkennungstools

  • src/services/: Gemini- und OpenAI-kompatible Anbieter

  • src/types/: gemeinsame Typen

  • src/utils/: Hilfsfunktionen

Lizenz

MIT

Available Tools

3 tools
audio_recognitionB

Analyze and transcribe audio using Google Gemini AI

ParametersJSON Schema
NameRequiredDescriptionDefault
filepathYesPath to the media file to analyze
modelnameNoGemini model to use for recognitiongemini-2.0-flash
promptNoCustom prompt for the recognitionDescribe this content

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden of behavioral disclosure. It only states 'analyze and transcribe' but does not detail output format, processing behavior, authentication needs, or limitations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, front-loaded with the core purpose. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should explain what the tool returns (e.g., transcribed text or analysis). It does not, nor does it cover edge cases or prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all parameters. The description does not add additional meaning beyond what the schema provides, meeting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: analyze and transcribe audio using Google Gemini AI. It explicitly mentions 'audio' which distinguishes it from sibling tools image_recognition and video_recognition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs alternatives (e.g., image_recognition, video_recognition). The description only states what it does without context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

image_recognitionB

Analyze and describe images using Google Gemini AI

ParametersJSON Schema
NameRequiredDescriptionDefault
filepathYesPath to the media file to analyze
modelnameNoGemini model to use for recognitiongemini-2.0-flash
promptNoCustom prompt for the recognitionDescribe this content

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only mentions 'using Google Gemini AI' but does not disclose safety (e.g., read-only vs destructive), API costs, file size limits, or the nature of the analysis (e.g., real-time, batch).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with verb and resource. No wasted words. Efficient and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is provided, yet the description does not explain what the tool returns (e.g., text description, confidence scores). For a tool with 3 parameters and no annotations, this leaves the agent guessing about the response format and behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with each parameter described. The description adds no additional meaning beyond the schema; it only names the AI provider. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Analyze and describe images') and the technology ('using Google Gemini AI'). It distinguishes from sibling tools (audio_recognition, video_recognition) by specifying the media type (images).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., audio_recognition, video_recognition). No mention of prerequisites, limitations, or scenarios where it is not appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

video_recognitionC

Analyze and describe videos using Google Gemini AI

ParametersJSON Schema
NameRequiredDescriptionDefault
filepathYesPath to the media file to analyze
modelnameNoGemini model to use for recognitiongemini-2.0-flash
promptNoCustom prompt for the recognitionDescribe this content

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool analyzes and describes videos but doesn't mention critical behavioral aspects like rate limits, authentication requirements, file size limits, supported video formats, processing time, or error handling. The description is too vague about what 'analyze and describe' entails operationally.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that states the core functionality without unnecessary words. It's appropriately sized and front-loaded with the essential information, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of video analysis (which typically involves format handling, processing time, and potential errors), no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns, how to interpret results, or any operational constraints, leaving significant gaps for an AI agent to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema, such as explaining how the prompt interacts with video analysis or model selection trade-offs. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as analyzing and describing videos using Google Gemini AI, which is specific (verb+resource) and distinguishes it from sibling tools like audio_recognition and image_recognition. However, it doesn't explicitly mention video-specific capabilities beyond the name, leaving some ambiguity about whether it handles all video formats or specific features.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its siblings (audio_recognition, image_recognition). It doesn't mention prerequisites, limitations, or alternative scenarios, leaving the agent to infer usage based on tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedaudio_recognition
    • First observedimage_recognition
    • First observedvideo_recognition
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.2/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting different media types: audio, images, and videos. There is no overlap in functionality, as they handle separate input formats with similar analysis capabilities but different domains.

Naming Consistency5/5

All tool names follow a consistent pattern of 'media_type_recognition' using snake_case. This predictable naming scheme makes it easy to understand what each tool does based on its name alone.

Tool Count3/5

With only 3 tools, the server feels somewhat thin for a video recognition domain, as it lacks operations like video editing, frame extraction, or metadata retrieval. However, the core recognition functions for audio, images, and videos are covered, making it borderline appropriate.

Completeness3/5

The server provides basic recognition for three media types but lacks comprehensive coverage for video processing. There are no tools for operations like video segmentation, object tracking, or format conversion, which are common in video recognition workflows, leaving notable gaps.

Maintenance

ActivitySlowing
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches