MCP Docent Server provides an image-description tool through a local TypeScript FastMCP server backed by an OpenAI client.
MCP Docent Server provides an image-description tool through a local TypeScript FastMCP server backed by an OpenAI client.
This community project registers an image-description tool and starts a FastMCP server over stdio. It is intended for generating explanatory text from a supplied image. The entry point and tool implementation are in the TypeScript source, separate from the generated model description.
Install the project dependencies and compile it with the documented TypeScript build script. Register dist/index.js as the local Node process. Configure the model-client credentials required by the tool implementation; the package metadata alone does not establish a separately published runnable npm binary.
Use a test image with a simple, recognizable subject and compare the returned description with the visible details. Ask the assistant to separate observed elements from inferred context. A fluent description can still invent a location, identity or event that the image does not show. Inspect supported inputs and error handling before depending on the server for a document or accessibility workflow.
{
"mcpServers": {
"mcp-docent": {
"command": "node",
"args": [
"/ABSOLUTE_PATH/mcp-docent-server/dist/index.js"
]
}
}
}Node.js, the built project and credentials configured as required by the image-description tool implementation.
Enables AI assistants to control Spotify playback and manage playlists via the Model Context Protocol.
Allows AI assistants to query movie and TV show collections managed by Radarr and Sonarr.
This community Workers MCP demo exposes image generation, page screenshots and image extraction through a local client adapter and Cloudflare backend.
Analyzes YouTube videos by extracting transcripts, summarizing content, and answering questions using AI.
Retrieves YouTube video URLs from a specified Watch Later playlist within a given timeframe.
Provides QQ Music search functionality via the Modular Control Protocol (MCP).