Minima

Local

API Integration

Integrate this MCP server into your applications.

Get your API Key

You'll need to login and generate a Smithery API key to connect to this server.

Installation

Install the official MCP SDKs using npm:

bash

npm install @modelcontextprotocol/sdk @smithery/sdk

TypeScript SDK

typescript


import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js"

const transport = new StdioClientTransport({
  "command": "python",
  "args": [
    "-m",
    "uv",
    "--directory",
    "/path_to_cloned_minima_project/mcp-server",
    "run",
    "minima"
  ],
  "env": {
    "LOCAL_FILES_PATH": "/path/to/folder",
    "EMBEDDING_MODEL_ID": "sentence-transformers/all-mpnet-base-v2",
    "EMBEDDING_SIZE": "768",
    "START_INDEXING": "true",
    "OLLAMA_MODEL": "qwen2:0.5b",
    "RERANKER_MODEL": "BAAI/bge-reranker-base"
  }
})

// Create MCP client
import { Client } from "@modelcontextprotocol/sdk/client/index.js"

const client = new Client({
	name: "Test client",
	version: "1.0.0"
})
await client.connect(transport)

// Use the server tools with your LLM application
const tools = await client.listTools()
console.log(`Available tools: ${tools.map(t => t.name).join(", ")}`)

Configuration Schema

Full JSON Schema for server configuration:

json

{
  "type": "object",
  "required": [
    "localFilesPath",
    "embeddingModelId",
    "embeddingSize",
    "startIndexing",
    "ollamaModel",
    "rerankerModel"
  ],
  "properties": {
    "ollamaModel": {
      "type": "string",
      "description": "The Ollama model ID for LLM."
    },
    "embeddingSize": {
      "type": "number",
      "description": "The embedding dimension provided by the model."
    },
    "rerankerModel": {
      "type": "string",
      "description": "The reranker model ID."
    },
    "startIndexing": {
      "type": "boolean",
      "description": "Flag to begin indexing. Set to true on initial run."
    },
    "localFilesPath": {
      "type": "string",
      "description": "Path to the root folder for indexing."
    },
    "embeddingModelId": {
      "type": "string",
      "description": "The embedding model ID to use."
    }
  }
}