mcp-meilisearch 1.2.4 → 1.2.5

package/README.md

@@ -1,33 +1,19 @@
 # MCP Meilisearch API Server
 
-A Model Context Protocol (MCP) server implementation that provides a bridge between AI models and the Meilisearch search engine using the StreamableHTTP transport. This project enables seamless integration of Meilisearch's powerful search capabilities within AI workflows.
+A Model Context Protocol (MCP) server implementation that provides a bridge between AI models and the Meilisearch search engine.
 
-## Updated Overview
-
-This project provides a MCP server that enables AI models to interact directly with Meilisearch functionalities. The architecture includes:
+## Overview
 
 - **MCP Server**: Exposes Meilisearch APIs as tools using the Model Context Protocol.
 - **Web Client Demo**: A demo interface showcasing search functionalities.
 
 ## Key Features
 
-- **StreamableHTTP Transport**: Real-time communication between clients and the server.
+- **Multiple Transport Options**: Supports both STDIO and StreamableHTTP transports.
+- **Real-time Communication**: Enables seamless interaction between clients and the server.
 - **Meilisearch API Support**: Full access to Meilisearch functionalities.
-- **Enhanced Error Handling**: Improved error management for API requests.
 - **Web Client Demo**: Updated interface for demonstrating search capabilities.
 
-## Tool Categories
-
-The MCP server organizes Meilisearch APIs into these categories:
-
-1. **System Tools**: Health checks, version info, server stats.
-2. **Index Tools**: Manage indexes (create, update, delete, list).
-3. **Document Tools**: Add, update, delete, and retrieve documents.
-4. **Search Tools**: Advanced search, including vector search.
-5. **Settings Tools**: Configure index settings.
-6. **Task Tools**: Manage asynchronous tasks.
-7. **Vector Tools**: Experimental vector search capabilities.
-
 ## Getting Started
 
 ### Prerequisites
@@ -36,57 +22,68 @@ The MCP server organizes Meilisearch APIs into these categories:
 - A running Meilisearch instance (local or remote).
 - API key for Meilisearch (if required).
 
-### Setup Instructions
+### Installation
 
-1. Clone the repository:
+Install the package:
 
 ```bash
-git clone https://github.com/falcosan/mcp
-```
+# Using npm
+npm install mcp-meilisearch
 
-2. Install dependencies:
+# Using yarn
+yarn add mcp-meilisearch
 
-```bash
-npm install
+# Using pnpm
+pnpm add mcp-meilisearch
 ```
 
-3. Configure the environment:
+### Options
 
-Create a `.env` file with the following content:
+#### Meilisearch Connection Options
 
-```
-MEILISEARCH_HOST=http://localhost:7700
-MEILISEARCH_API_KEY=your_master_key_here
-```
+- `meilisearchHost`: URL of the Meilisearch instance (Default: "http://localhost:7700")
+- `meilisearchApiKey`: API key for authenticating with Meilisearch (Default: "")
+
+#### MCP Server Options
 
-### Running the Server
+- `transport`: Transport type for MCP server ("http" | "stdio") (Default: "http")
+- `httpPort`: HTTP port for MCP server (Default: 4995)
+- `mcpEndpoint`: MCP endpoint path (Default: "/mcp")
 
-To start the server:
+#### Session Options
 
-```bash
-npm run server  # Start the MCP server
-npm run demo  # Start the Web client demo
-```
+- `sessionTimeout`: Session timeout in milliseconds (Default: 3600000)
+- `sessionCleanupInterval`: Session cleanup interval in milliseconds (Default: 60000)
 
-### Accessing the Web Interface
+### Using the MCPClient
 
-Visit the following URL in your browser:
+The package also exports the MCPClient class for client-side integration:
 
-```
-http://localhost:8080
-```
+```typescript
+import { MCPClient } from "mcp-meilisearch/client";
+
+const client = new MCPClient("mcp-meilisearch-client");
+await client.connectToServer("http://localhost:4995/mcp");
 
-## Development
+// Call a tool
+const result = await client.callTool("search-across-all-indexes", {
+  q: "search kiosco antonio",
+});
+```
 
-This project uses:
+## Tools
 
-- **TypeScript**: Ensures type safety.
-- **Express**: Powers the web server.
-- **Model Context Protocol SDK**: Facilitates AI integration.
+The MCP server exposes various tools that allow you to interact with Meilisearch functionalities. Each tool corresponds to a specific Meilisearch API endpoint, enabling you to perform operations such as searching, indexing, and managing documents.
 
-## Available Tools
+### Tool Categories
 
-This section details all the available tools, their descriptions, and parameters.
+1. **System Tools**: Health checks, version info, server stats.
+2. **Index Tools**: Manage indexes (create, update, delete, list).
+3. **Document Tools**: Add, update, delete, and retrieve documents.
+4. **Search Tools**: Advanced search, including vector search.
+5. **Settings Tools**: Configure index settings.
+6. **Task Tools**: Manage asynchronous tasks.
+7. **Vector Tools**: Experimental vector search capabilities.
 
 ### System Tools
 
@@ -386,37 +383,3 @@ This section details all the available tools, their descriptions, and parameters
   - `query` (string, optional): Text query to search for (if using 'embedder' instead of 'vector').
   - `hybrid` (boolean, optional): Whether to perform a hybrid search (combining vector and text search).
   - `hybridRatio` (number, optional): Ratio of vector vs text search in hybrid search (0-1, default: 0.5).
-
-### Options
-
-#### Meilisearch Connection Options
-
-- `meilisearchHost`: URL of the Meilisearch instance (Default: "http://localhost:7700")
-- `meilisearchApiKey`: API key for authenticating with Meilisearch (Default: "")
-
-#### MCP Server Options
-
-- `transport`: Transport type for MCP server ("http" | "stdio") (Default: "http")
-- `httpPort`: HTTP port for MCP server (Default: 4995)
-- `mcpEndpoint`: MCP endpoint path (Default: "/mcp")
-
-#### Session Options
-
-- `sessionTimeout`: Session timeout in milliseconds (Default: 3600000)
-- `sessionCleanupInterval`: Session cleanup interval in milliseconds (Default: 60000)
-
-### Using the MCPClient
-
-The package also exports the MCPClient class for client-side integration:
-
-```typescript
-import { MCPClient } from "mcp-meilisearch/client";
-
-const client = new MCPClient("mcp-meilisearch-client");
-await client.connectToServer("http://localhost:4995/mcp");
-
-// Call a tool
-const result = await client.callTool("search-across-all-indexes", {
-  q: "search kiosco antonio",
-});
-```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-meilisearch",
-  "version": "1.2.4",
+  "version": "1.2.5",
   "description": "Model Context Protocol (MCP) implementation for Meilisearch",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",