Feat: add model context protocol (#40)

* Refactor main.ts to move search request and normal mode into search.ts

* Add model context protocol server

* Use .actor/input_schema.json as input for MCP

.dockerignore

@@ -14,3 +14,5 @@ node_modules
 
 # data
 data
+src/storage
+dist

CHANGELOG.md

@@ -1,6 +1,11 @@
 This changelog summarizes all changes of the RAG Web Browser
 
-### 2024-11-13
+### 1.0.4 (2025-01-04)
+
+🚀 Features
+- Include Model Context Protocol in Standby Mode
+
+### 1.0.3 (2024-11-13)
 
 🚀 Features
 - Improve README.md and simplify configuration
@@ -11,13 +16,13 @@ This changelog summarizes all changes of the RAG Web Browser
 - Rename googleSearchResults to searchResults and searchProxyGroup to serpProxyGroup
 - Implement input validation
 
-### 2024-11-08
+### 0.1.4 (2024-11-08)
 
 🚀 Features
 - Add functionality to extract content from a specific URL
 - Update README.md to include new functionality and provide examples
 
-### 2024-10-17
+### 0.0.32 (2024-10-17)
 
 🚀 Features
 - Handle errors when request is added to Playwright queue.

README.md

@@ -159,9 +159,45 @@ Learn more about [adding custom actions to your GPTs with Apify Actors](https://
 
 The RAG Web Browser Actor can also be used as an [MCP server](https://github.com/modelcontextprotocol) and integrated with AI applications and agents, such as Claude Desktop.
 For example, in Claude Desktop, you can configure the MCP server in its settings to perform web searches and extract content.
-
 Alternatively, you can develop a custom MCP client to interact with the RAG Web Browser Actor.
 
+In the Standby mode, the Actor runs an HTTP server that supports the MCP protocol via SSE (Server-Sent Events).
+
+1. Initiate SSE connection:
+    ```shell
+    curl https://rag-web-browser.apify.actor/sse?token=<APIFY_API_TOKEN>
+    ```
+    On connection, you’ll receive a `sessionId`:
+    ```text
+    event: endpoint
+    data: /message?sessionId=5b2
+    ```
+
+1. Send a message to the server by making a POST request with the `sessionId`, `APIFY-API-TOKEN` and your query:
+    ```shell
+    curl -X POST "https://rag-web-browser.apify.actor/message?session_id=5b2&token=<APIFY-API-TOKEN>" -H "Content-Type: application/json" -d '{
+      "jsonrpc": "2.0",
+      "id": 1,
+      "method": "tools/call",
+      "params": {
+        "arguments": { "query": "recent news about LLMs", "maxResults": 1 },
+        "name": "rag-web-browser"
+      }
+    }'
+    ```
+    For the POST request, the server will respond with:
+    ```text
+    Accepted
+    ```
+
+1. Receive a response at the initiated SSE connection:
+   The server invoked `Actor` and its tool using the provided query and sent the response back to the client via SSE.
+
+    ```text
+    event: message
+    data: {"result":{"content":[{"type":"text","text":"[{\"searchResult\":{\"title\":\"Language models recent news\",\"description\":\"Amazon Launches New Generation of LLM Foundation Model...\"}}
+    ```
+
 To learn more about MCP server integration, check out the [RAG Web Browser MCP server documentation](https://github.com/apify/mcp-server-rag-web-browser).
 
 ## ⏳ Performance optimization
@@ -277,3 +313,9 @@ And then you can run it locally using [Apify CLI](https://docs.apify.com/cli) as
 ```bash
 APIFY_META_ORIGIN=STANDBY apify run -p
 ```
+
+Server will start on `http://localhost:3000` and you can send requests to it, for example:
+
+```bash
+curl "http://localhost:3000/search?query=example.com"
+```