Tester MCP Client avatar
Tester MCP Client

Pricing

Pay per event

Go to Store
Tester MCP Client

Tester MCP Client

Developed by

Jiří Spilka

Maintained by Apify

A model context protocol (MCP) client that connects to any MCP server using Server-Sent Events (SSE) and displays the conversation in a chat-like UI. It is a standalone Actor server designed for testing MCP servers over SSE.

4.8 (5)

Pricing

Pay per event

10

Monthly users

118

0

Last modified

13 days ago

You can access the Tester MCP Client programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.

1# Start Server-Sent Events (SSE) session and keep it running
2curl "https://actors-mcp-server.apify.actor/sse?token=<YOUR_API_TOKEN>&actors=jiri.spilka/tester-mcp-client"
3
4# Session id example output:
5# event: endpoint
6# data: /message?sessionId=9d820491-38d4-4c7d-bb6a-3b7dc542f1fa

Using Tester MCP Client via Model Context Protocol (MCP) server

MCP server lets you use Tester MCP Client within your AI workflows. Send API requests to trigger actions and receive real-time results. Take the received sessionId and use it to communicate with the MCP server. The message starts the Tester MCP Client Actor with the provided input.

1curl -X POST "https://actors-mcp-server.apify.actor/message?token=<YOUR_API_TOKEN>&session_id=<SESSION_ID>" -H "Content-Type: application/json" -d '{
2  "jsonrpc": "2.0",
3  "id": 1,
4  "method": "tools/call",
5  "params": {
6    "arguments": {
7      "mcpSseUrl": "https://actors-mcp-server.apify.actor/sse?enableActorAutoLoading=true",
8      "systemPrompt": "You are a helpful Apify assistant with to tools called Actors.\\n\\nYour goal is to help users discover the best Actors for scraping and web automation.\\nYou have access to a list of tools that can help you to discover Actors, find details and include them among tools for later execution.\\n\\nChoose the appropriate Actor based on the conversation context. If no Actor is needed, reply directly.\\n\\nPrefer Actors with more users, stars, and runs\\nWhen you need to use an Actor, explain how it used and with which parameters.\\nNever call an Actor unless it is required by user!\\nAfter receiving a Actors'\'' response:\\n1. Transform the raw data into a natural, conversational response\\n2. Keep responses concise but informative\\n3. Focus on the most relevant information\\n4. Use appropriate context from the user'\''s question\\n5. Avoid simply repeating the raw data\\nAlways use Actor not actor. Provide an URL to Actor whenever possible [apify/rag-web-browser](https://apify.com/apify/rag-web-browser).\\nREMEMBER Always limit number of results returned from Actors.\\nThere is always parameter such as maxResults=1, maxPage=1, maxCrawledPlacesPerSearch=1, keep it to minimal value. \\nOtherwise Actor execution takes long and result is huge!Always inform user that calling Actor might take some time.\\n",
9      "modelMaxOutputTokens": 2048,
10      "maxNumberOfToolCallsPerQuery": 5,
11      "toolCallTimeoutSec": 300
12},
13    "name": "jiri.spilka/tester-mcp-client"
14  }
15}'

The response should be: Accepted. You should received response via SSE (JSON) as:

1event: message
2data: {
3  "result": {
4    "content": [
5      {
6        "type": "text",
7        "text": "ACTOR_RESPONSE"
8      }
9    ]
10  }
11}

Configure local MCP Server via standard input/output for Tester MCP Client

You can connect to the MCP Server using clients like ClaudeDesktop and LibreChat or build your own. The server can run both locally and remotely, giving you full flexibility. Set up the server in the client configuration as follows:

1{
2  "mcpServers": {
3    "actors-mcp-server": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "@apify/actors-mcp-server",
8        "--actors",
9        "jiri.spilka/tester-mcp-client"
10      ],
11      "env": {
12        "APIFY_TOKEN": "<YOUR_API_TOKEN>"
13      }
14    }
15  }
16}

You can further access the MCP client through the Tester MCP Client, a chat user interface to interact with the server.

To get started, check out the documentation and example clients. If you are interested in learning more about our MCP server, check out our blog post.

Pricing

Pricing model

Pay per event 

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Actor start

$0.005

Flat fee for starting an Actor run.

Actor running time (5 minutes)

$0.005

Cost per running time for each 5 minutes.

Input tokens (Sonnet-3.7)

$0.000

Cost per 100 input tokens for Claude 3.7 Sonnet (1M tokens = 3$).

Output tokens (Sonnet-3.7)

$0.002

Cost per 100 output tokens for Claude 3.7 Sonnet (1M tokens = 15$).

Input tokens (Haiku-3.5)

$0.000

Cost per 100 input tokens for Claude 3.5 Haiku (1M tokens = 0.8$).

Output tokens (Haiku-3.5)

$0.000

Cost per 100 output tokens for Claude 3.5 Haiku (1M tokens = 4$).

Query answered

$0.005

Cost per query answered.