About Pocha MCP Server
Pocha MCP Server generates typed TypeScript API function templates for the Pocha project. It is intended for development teams that want consistent functions with HTTP method, authentication, and error-handling support.
Key features
- 01Generate typed TypeScript API functions
- 02Support GET, POST, PUT, and DELETE
- 03Handle authentication tokens
- 04Include error handling and response typing
- 05Allow optional parameters and return types
Use cases
- 01Create a typed function for a Pocha API route
- 02Generate API templates with consistent error handling
MCP support
The MCP server exposes the generate-api-function tool, which accepts function details such as the route, HTTP method, and optional parameters.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPocha MCP Server
A Model Context Protocol (MCP) server that generates TypeScript API functions for the Pocha project. This server provides a tool to automatically generate type-safe API function templates following a consistent pattern.
Features
- Generates TypeScript API functions with proper typing
- Supports GET, POST, PUT, DELETE HTTP methods
- Includes authentication token handling
- Generates proper error handling and response typing
- Supports optional parameters and return types
Installation
# Clone the repository
git clone https://github.com/jiohjung98/pocha-mcp-server.git
# Install dependencies
pnpm install
# Build the project
pnpm build
Usage
The server provides a tool called generate-api-function that accepts the following parameters:
{
functionName: string; // Name of the API function to generate
route: string; // API route path (e.g., "/pocha/${pochaid}")
method: "GET" | "POST" | "PUT" | "DELETE"; // HTTP method
params?: { // Optional array of parameters
name: string; // Parameter name
type: string; // Parameter type
}[];
returnType: string; // Return type of the API function
}
Example
To generate an API function for fetching Pocha information:
// Input parameters
{
"functionName": "getPocha",
"route": "/pocha/${pochaid}",
"method": "GET",
"params": [
{
"name": "pochaid",
"type": "number"
}
],
"returnType": "PochaInfo"
}
// Generated output
/**
* @desc getPocha
* @route GET /pocha/${pochaid}
*/
export async function getPocha(pochaid: number, token: string): Promise<PochaInfo> {
const url = `/pocha/${pochaid}`;
try {
const response = await client.get(url, {
headers: {
Authorization: `Bearer ${token}`,
},
});
return response?.data;
} catch (error) {
console.log(error);
throw new Error("Error in getPocha");
}
}
Development
The server is built using:
- TypeScript
- MCP TypeScript SDK
- Zod for schema validation
To start development:
# Install dependencies
pnpm install
# Build in watch mode
pnpm dev
Project Structure
pocha-mcp-server/
├── src/
│ └── index.ts # Main server implementation
├── dist/ # Compiled JavaScript
├── package.json
└── tsconfig.json
Cursor Setup
To use this MCP server in your Cursor IDE:
-
Open your Cursor MCP configuration file:
# macOS ~/.cursor/mcp.json # Windows %APPDATA%/cursor/mcp.json # Linux ~/.cursor/mcp.json -
Add the following configuration to the
mcpServersobject:{ "mcpServers": { "pocha-api-generator": { "command": "/opt/homebrew/bin/npx", "args": ["-y", "node", "/path/to/your/pocha-mcp-server/dist/index.js"] } } }Replace
/path/to/your/pocha-mcp-serverwith the actual path where you cloned this repository. -
Restart Cursor for the changes to take effect.
-
The MCP server will now be available in Cursor, and you can use it to generate API functions by typing natural language commands like:
Can you create a sample API for pocha project that fetches PochaInfo from "/pocha/${pochaid}" using "pocha-api-generator" mcp?
License
MIT License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.