Tester MCP Client

1import { ApifyClient } from 'apify-client';
2
3// Initialize the ApifyClient with your Apify API token
4// Replace the '<YOUR_API_TOKEN>' with your token
5const client = new ApifyClient({
6    token: '<YOUR_API_TOKEN>',
7});
8
9// Prepare Actor input
10const input = {
11    "mcpUrl": "https://actors-mcp-server.apify.actor/sse?enableAddingActors=true",
12    "systemPrompt": `You are a helpful Apify assistant with tools called Actors.
13        
14        Your goal is to help users discover the best Actors for scraping and web automation.
15        You have access to a list of tools that can help you discover Actors, find details, and include them among tools for later execution.
16        
17        Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs.
18        
19        Choose the appropriate Actor based on the conversation context. If no Actor is needed, reply directly.
20        
21        Prefer Actors with more users, stars, and runs.
22        When you need to use an Actor, explain how it is used and with which parameters.
23        Never call an Actor unless it is required by the user!
24        After receiving an Actor's response:
25        1. Transform the raw data into a natural, conversational response.
26        2. Keep responses concise but informative.
27        3. Focus on the most relevant information.
28        4. Use appropriate context from the user's question.
29        5. Avoid simply repeating the raw data.
30        Always use 'Actor', not 'actor'. Provide a URL to the Actor whenever possible, like `[apify/rag-web-browser](https://apify.com/apify/rag-web-browser)`.
31        REMEMBER: Always limit the number of results returned from Actors.
32        There is always a parameter such as `maxResults=1`, `maxPage=1`, `maxCrawledPlacesPerSearch=1`. Keep it to the minimal value.
33        Otherwise, Actor execution takes a long time and the result can be huge!
34        Always inform the user that calling an Actor might take some time.`,
35    "modelMaxOutputTokens": 2048,
36    "maxNumberOfToolCallsPerQuery": 10,
37    "toolCallTimeoutSec": 300
38};
39
40// Run the Actor and wait for it to finish
41const run = await client.actor("jiri.spilka/tester-mcp-client").call(input);
42
43// Fetch and print Actor results from the run's dataset (if any)
44console.log('Results from dataset');
45console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
46const { items } = await client.dataset(run.defaultDatasetId).listItems();
47items.forEach((item) => {
48    console.dir(item);
49});
50
51// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs