Model Context Protocol Server
# my-mcp-server
A Model Context Protocol (MCP) server built with mcp-framework.
## Quick Start
```bash
# Install dependencies
npm install
# Build the project
npm run build
```
## Project Structure
```
my-mcp-server/
├── src/
│ ├── tools/ # MCP Tools
│ │ └── ExampleTool.ts
│ └── index.ts # Server entry point
├── package.json
└── tsconfig.json
```
## Adding Components
The project comes with an example tool in `src/tools/ExampleTool.ts`. You can add more tools using the CLI:
```bash
# Add a new tool
mcp add tool my-tool
# Example tools you might create:
mcp add tool data-processor
mcp add tool api-client
mcp add tool file-handler
```
## Tool Development
Example tool structure:
```typescript
import { MCPTool } from "mcp-framework";
import { z } from "zod";
interface MyToolInput {
message: string;
}
class MyTool extends MCPTool<MyToolInput> {
name = "my_tool";
description = "Describes what your tool does";
schema = {
message: {
type: z.string(),
description: "Description of this input parameter",
},
};
async execute(input: MyToolInput) {
// Your tool logic here
return `Processed: ${input.message}`;
}
}
export default MyTool;
```
## Publishing to npm
1. Update your package.json:
- Ensure `name` is unique and follows npm naming conventions
- Set appropriate `version`
- Add `description`, `author`, `license`, etc.
- Check `bin` points to the correct entry file
2. Build and test locally:
```bash
npm run build
npm link
my-mcp-server # Test your CLI locally
```
3. Login to npm (create account if necessary):
```bash
npm login
```
4. Publish your package:
```bash
npm publish
```
After publishing, users can add it to their claude desktop client (read below) or run it with npx
```
## Using with Claude Desktop
### Local Development
Add this configuration to your Claude Desktop config file:
**MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"my-mcp-server": {
"command": "node",
"args":["/absolute/path/to/my-mcp-server/dist/index.js"]
}
}
}
```
### After Publishing
Add this configuration to your Claude Desktop config file:
**MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"my-mcp-server": {
"command": "npx",
"args": ["my-mcp-server"]
}
}
}
```
## Building and Testing
1. Make changes to your tools
2. Run `npm run build` to compile
3. The server will automatically load your tools on startup
## Learn More
- [MCP Framework Github](https://github.com/QuantGeekDev/mcp-framework)
- [MCP Framework Docs](https://mcp-framework.com)
TDQS
Scored across 3 tools
The 'weather' and 'weather_api' tools have significant overlap in purpose, as both appear to fetch weather information for a city, making them ambiguous and prone to misselection. The 'example_tool' is distinct but vague, adding to the overall confusion in the tool set.
The naming is mixed with 'example_tool' and 'weather_api' using snake_case, while 'weather' is a single word, showing some inconsistency. However, the names are still readable and follow a basic pattern, but lack a uniform verb_noun structure or consistent style.
With only 3 tools, the count is borderline thin for a general-purpose server like 'Model Context Protocol Server', suggesting it might be under-scoped. While not extreme, it feels insufficient to cover a broad domain effectively, indicating a potential mismatch in scope.
The tool set is severely incomplete for the server's implied domain, with overlapping weather tools and a vague example tool, leaving obvious gaps in functionality. There is no clear coverage of core operations or a coherent workflow, which will likely cause agent failures due to missing essential capabilities.