image-reader MCP Server
# image-reader MCP Server
image reader
This is a TypeScript-based MCP server that implements a simple notes system. It demonstrates core MCP concepts by providing:
- Resources representing text notes with URIs and metadata
- Tools for creating new notes
- Prompts for generating summaries of notes
## Features
### Resources
- List and access notes via `note://` URIs
- Each note has a title, content and metadata
- Plain text mime type for simple content access
### Tools
- `create_note` - Create new text notes
- Takes title and content as required parameters
- Stores note in server state
### Prompts
- `summarize_notes` - Generate a summary of all stored notes
- Includes all note contents as embedded resources
- Returns structured prompt for LLM summarization
## Development
Install dependencies:
```bash
npm install
```
Build the server:
```bash
npm run build
```
For development with auto-rebuild:
```bash
npm run watch
```
## Installation
To use with Claude Desktop, add the server config:
On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"image-reader": {
"command": "/path/to/image-reader/build/index.js"
}
}
}
```
### Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:
```bash
npm run inspector
```
The Inspector will provide a URL to access debugging tools in your browser.
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: analyze_image extracts metadata, convert_format changes file type, resize_image adjusts dimensions, and scan_directory finds images in a directory. There is no overlap or ambiguity between these functions.
All tools follow a consistent verb_noun pattern (e.g., analyze_image, convert_format, resize_image, scan_directory). The naming is uniform and predictable throughout the set.
With 4 tools, this server is well-scoped for basic image processing tasks. Each tool serves a clear, essential function without redundancy, making the count appropriate for the domain.
The toolset covers key operations like metadata extraction, format conversion, resizing, and directory scanning, which are core to image reading. A minor gap might be the lack of tools for editing (e.g., cropping or filtering), but the provided tools are sufficient for basic workflows.