Feature/740 multi server chatbot example

examples/client/.env.example

@@ -0,0 +1,3 @@
+# LLM API Key
+# Get your API key from your LLM provider (OpenAI, Groq, etc.)
+LLM_API_KEY=your_api_key_here

examples/client/README.md

@@ -26,6 +26,7 @@ Most clients expect a server to be running. Start one from [`../server/README.md
 
 | Scenario                                            | Description                                                                               | File                                                                                       |
 | --------------------------------------------------- | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
+| Simple multi-server chatbot                         | CLI chatbot connecting to multiple MCP servers via STDIO with LLM integration.            | [`src/simpleChatbot.ts`](src/simpleChatbot.ts)                                             |
 | Interactive Streamable HTTP client                  | CLI client that exercises tools/resources/prompts, notifications, elicitation, and tasks. | [`src/simpleStreamableHttp.ts`](src/simpleStreamableHttp.ts)                               |
 | Backwards-compatible client (Streamable HTTP → SSE) | Tries Streamable HTTP first, falls back to legacy SSE on 4xx responses.                   | [`src/streamableHttpWithSseFallbackClient.ts`](src/streamableHttpWithSseFallbackClient.ts) |
 | SSE polling client (legacy)                         | Polls a legacy HTTP+SSE server and demonstrates notification handling.                    | [`src/ssePollingClient.ts`](src/ssePollingClient.ts)                                       |
@@ -37,6 +38,41 @@ Most clients expect a server to be running. Start one from [`../server/README.md
 | URL elicitation client                              | Drives URL-mode elicitation flows (sensitive input in a browser).                         | [`src/elicitationUrlExample.ts`](src/elicitationUrlExample.ts)                             |
 | Task interactive client                             | Demonstrates task-based execution + interactive server→client requests.                   | [`src/simpleTaskInteractiveClient.ts`](src/simpleTaskInteractiveClient.ts)                 |
 
+## Simple chatbot example
+
+The simple chatbot demonstrates connecting to multiple MCP servers simultaneously and integrating with an LLM provider.
+
+**Configuration:**
+
+A `servers_config.json` file is included with default server configurations. You can edit it to add or modify servers:
+
+```json
+{
+    "mcpServers": {
+        "everything": {
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-everything"]
+        },
+        "memory": {
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-memory"]
+        }
+    }
+}
+```
+
+The chatbot will discover tools from all configured servers and allow interactive conversation. Type `quit` or `exit` to end the session.
+
+**Running:**
+
+```bash
+# Set your LLM API key (OpenAI, Groq, etc.)
+export LLM_API_KEY=your_api_key_here
+
+# Run the chatbot
+pnpm --filter @modelcontextprotocol/examples-client exec tsx src/simpleChatbot.ts
+```
+
 ## URL elicitation example (server + client)
 
 Run the server first:

examples/client/package.json

@@ -43,6 +43,7 @@
         "@modelcontextprotocol/tsconfig": "workspace:^",
         "@modelcontextprotocol/eslint-config": "workspace:^",
         "@modelcontextprotocol/vitest-config": "workspace:^",
-        "tsdown": "catalog:devTools"
+        "tsdown": "catalog:devTools",
+        "vitest": "catalog:devTools"
     }
 }

examples/client/servers_config.example.json

@@ -0,0 +1,8 @@
+{
+    "mcpServers": {
+        "weather": {
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-everything"]
+        }
+    }
+}

examples/client/servers_config.json

@@ -0,0 +1,12 @@
+{
+    "mcpServers": {
+        "everything": {
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-everything"]
+        },
+        "memory": {
+            "command": "npx",
+            "args": ["-y", "@modelcontextprotocol/server-memory"]
+        }
+    }
+}