readme updated

README.md

@@ -1,70 +1,108 @@
-# Gemini MCP Client
+# MCP Client
 
-A TypeScript client library for interacting with Gemini MCP (Multi-Cloud Platform) services.
+A TypeScript client library for interacting with Model Context Protocol (MCP) services, providing a production-ready interface for AI conversations with tool support.
 
 ## Installation
 
 ```bash
-npm install gemini-mcp
+npm install https://git.everydayseries.io/kroy665/client-mcp.git
 ```
 
 ## Features
 
 - TypeScript support out of the box
-- Promise-based API
-- Comprehensive type definitions
-- Easy integration with Node.js applications
+- Streaming chat completions
+- Tool and function calling support
+- Automatic conversation management
+- Configurable connection to MCP servers
+- Debug logging
+- Request cancellation support
 
-## Usage
+## Quick Start
 
 ```typescript
-import { ClientMCP } from 'gemini-mcp';
+import { ClientMCP } from 'mcp-client';
 
-// Create a new instance
+// Create a new client instance
 const client = new ClientMCP({
   apiKey: 'your-api-key',
-  baseUrl: 'https://api.gemini-mcp.com/v1'
+  model: 'gemini-2.0-flash',
+  debug: true
 });
 
-// Use the client
-async function getBlogs() {
-  try {
-    const blogs = await client.getBlogs();
-    console.log(blogs);
-  } catch (error) {
-    console.error('Error fetching blogs:', error);
-  }
+// Connect to the MCP server
+await client.connectToServer('http://localhost:3003/mcp');
+
+// Stream chat responses
+for await (const chunk of client.chat("Hello, how are you?")) {
+  console.log(chunk.choices[0]?.delta?.content);
 }
 
-getBlogs();
+// Don't forget to clean up
+await client.disconnect();
 ```
 
 ## API Reference
 
 ### `new ClientMCP(config: ClientMCPConfig)`
 
-Creates a new Gemini MCP client instance.
+Creates a new MCP client instance.
 
 #### Parameters
 
 - `config` (Object): Configuration object
-  - `apiKey` (string): Your Gemini MCP API key
-  - `baseUrl` (string): Base URL for the API (default: 'https://api.gemini-mcp.com/v1')
+  - `apiKey` (string): Your API key for authentication
+  - `model` (string): The model to use (default: "gemini-2.0-flash")
+  - `baseUrl` (string): Base URL for the API
   - `timeout` (number): Request timeout in milliseconds (default: 30000)
+  - `debug` (boolean): Enable debug logging (default: false)
+  - `systemMessages` (string): Custom system messages (optional)
 
 ### Methods
 
-#### `getBlogs(): Promise<Blog[]>`
+#### `connectToServer(serverPath: string | URL, sessionId?: string): Promise<void>`
 
-Fetches all blogs for the authenticated user.
+Establishes connection to MCP server.
 
-#### `getBlog(id: string): Promise<Blog>`
+- `serverPath`: URL or string path to the MCP server
+- `sessionId`: Optional session ID for reconnection
 
-Fetches a specific blog by ID.
+#### `disconnect(): Promise<void>`
 
-#### `createBlog(blog: BlogCreate): Promise<Blog>`
+Disconnects from the MCP server and cleans up resources.
 
-Creates a new blog.
+#### `chatCompletionStream(options: ChatCompletionStreamOptions): AsyncGenerator<ChatCompletionChunk>`
+
+Performs streaming chat completion.
+
+```typescript
+const stream = client.chatCompletionStream({
+  messages: [{ role: 'user', content: 'Hello!' }],
+  reasoningEffort: 'high',
+  tools: [...]
+});
+
+for await (const chunk of stream) {
+  console.log(chunk.choices[0]?.delta?.content);
+}
+```
+
+#### `chat(content: string, options?: ChatOptions): AsyncGenerator<ChatChunk>`
+
+Main chat interface with automatic tool handling and conversation management.
+
+```typescript
+for await (const chunk of client.chat("What's the weather like?", {
+  maxDepth: 3,
+  autoSummarize: true
+})) {
+  process.stdout.write(chunk.choices[0]?.delta?.content || '');
+}
+```
+
+#### `cancelRequests(): void`
+
+Cancels all ongoing requests.
 
 ## Development
 
@@ -86,34 +124,10 @@ Creates a new blog.
 
 MIT
 
+## Notes
 
-TASK LIST
-
-npm version control
-
-add memory in it
-- function that can add data in memory 
-- function that can get data from memory dynamically using ai
-- update existing data in memory
-
-
-add tools search capabilities
-- function that can search tools dynamically using ai
-- function that can add tools dynamically using ai
-- save the tool usage in memory
-
-auto update prompts
-- prompts will be updated if user doesnot specify the result in the response.
-
-
-dynamicaly change the prompt when user query.
-- when user query it will determine what prompts to use as system prompt and other prompts
-
-
-add task listing capabilities in it
-- function that can list all the tasks and solve it
-
-Add branch out task capabilities in it(Advanced feature)
-
-
-
+- The client automatically manages conversation state and tool calls
+- Supports both HTTP and WebSocket transports
+- Includes comprehensive error handling and logging
+- Thread-safe for concurrent usage
+- Memory efficient with streaming support