Tester MCP Client
by
Connects to any MCP server via HTTP streamable or Server‑Sent Events (SSE) and presents the interaction in a chat‑like UI, allowing developers to test and debug MCP integrations quickly.
Tester MCP Client Overview
What is Tester MCP Client about?
A lightweight Actor that acts as a bridge between a browser UI and an MCP server. It opens an SSE channel to the client UI, forwards user messages to the MCP endpoint, receives streamed responses (including tool calls), and renders the whole conversation like a chat conversation.
How to use Tester MCP Client?
- Run on Apify – Click Try for free or start a new run from the Apify console. Provide the MCP server URL, optional system prompt, and API key if required.
- Local development – Clone the GitHub repo, run
npm installand start the client withnpm start. Openhttp://localhost:3000in a browser. - Interact – After the run starts, check the logs for a link to the UI (e.g.,
https://<run-id>.apify.net). Use the chat box to send queries; the UI will display LLM output and any tool usage.
Key features of Tester MCP Client
- Dual transport – Supports both recommended HTTP streamable and fallback SSE connections.
- Chat‑like UI – Real‑time display of LLM responses, tool calls, and results.
- Secure connections – Allows custom Authorization headers and API keys.
- Dynamic tool selection – Automatically invokes tools based on context when the MCP server supports it.
- Open source – Full source available on GitHub for review or modification.
- Pay‑per‑event pricing – Charged only for actor start, runtime, and answered queries.
Use cases of Tester MCP Client
- MCP server development – Validate server logic, tool integration, and response streaming.
- Debugging tool calls – Visualize how the server decides to invoke external tools.
- Performance testing – Measure latency and throughput of MCP endpoints using the built‑in SSE stream.
- Demo and training – Showcase MCP capabilities to stakeholders without writing custom UI code.
FAQ from the Tester MCP Client
- Do I need my own LLM API key? No. The client can use Apify’s built‑in LLM integration, but you may supply your own API key for lower costs.
- What is billed? Actor start, runtime (every 5 minutes), and each answered query. Using your own LLM key reduces LLM‑related charges.
- Can I run it locally? Yes. Clone the repo, run
npm installandnpm start, then open the local URL. - What MCP transports are supported? HTTP streamable (recommended) and Server‑Sent Events (SSE).
- Is the project open source? Yes, the code is hosted on GitHub and can be forked or contributed to.
Tester MCP Client's README
Tester MCP Client
Pricing
Pay per event
Tester MCP Client
Developed by
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.
5.0 (5)
Pricing
Pay per event
20
704
107
Last modified
6 days ago
READMEInputPricingAPISource codeIssues
Tester Client for Model Context Protocol (MCP)#tester-client-for-model-context-protocol-mcp
https://apify.com/jiri.spilka/tester-mcp-client
Implementation of a model context protocol (MCP) client that connects to an MCP server using HTTP streamable (recommended) or Server-Sent Events (SSE) transport and displays the conversation in a chat-like UI. It is a standalone Actor server designed for testing MCP servers over HTTP streamable or SSE. It uses Pay-per-event pricing model.
For more information, see the Model Context Protocol website or blogpost What is MCP and why does it matter?.
Once you run the Actor, check the output or logs for a link to the chat UI interface to interact with the MCP server. The URL will look like this and will vary each run:
Navigate to https://...apify.net to interact with chat-ui interface.
🚀 Main features#main-features
- 🔌 Connects to an MCP server using HTTP streamable (recommended) or Server-Sent Events (SSE)
- 💬 Provides a chat-like UI for displaying tool calls and results
- 🇦 Connects to an Apify MCP Server for interacting with one or more Apify Actors
- 💥 Dynamically uses tools based on context and user queries (if supported by a server)
- 🔓 Use Authorization headers and API keys for secure connections
- 🪟 Open source, so you can review it, suggest improvements, or modify it
🎯 What does Tester MCP Client do?#what-does-tester-mcp-client-do
When connected to Apify MCP Server the Tester MCP Client provides an interactive chat interface where you can:
- "What are the most popular Actors for social media scraping?"
- "Show me the best way to use the Instagram Scraper"
- "Which Actor should I use to extract data from LinkedIn?"
- "Can you help me understand how to scrape Google search results?"
📖 How does it work?#how-does-it-work
The Apify MCP Client connects to a running MCP server over HTTP streamable (recommended) or SSE and it does the following:
- Initiates a streamable HTTP connection to the MCP server or SSE connection (
/sse). - Sends user queries to the MCP server via
POST /message. - Receives real-time streamed responses (via
GET /sse) that may include LLM output, and tool usage blocks - Based on the LLM response, orchestrates tool calls and displays the conversation
- Displays the conversation
⚙️ Usage#usage
- Test any MCP server over SSE
- Test Apify MCP Server and the ability to dynamically select amongst thousands of tools
Learn about the key features and capabilities in the Apify MCP Server Tutorial: Integrate 5,000+ Apify Actors and Agents Into Claude video
Normal Mode (on Apify)#normal-mode-on-apify
You can run the Tester MCP Client on Apify and connect it to any MCP server that supports SSE. Configuration can be done via the Apify UI or API by specifying parameters such as the MCP server URL, system prompt, and API key.
Once you run Actor, check the logs for a link to the Tester MCP Client UI, where you can interact with the MCP server: The URL will look like this and will be different from run to run:
INFO Navigate to https://......runs.apify.net in your browser to interact with an MCP server.
💰 Pricing#pricing
The Apify MCP client uses a modern and flexible approach for AI Agents monetization and pricing called Pay-per-event. You only need to have Apify account and you can use it, LLM provider API key is not required but you can supply it if you want to use your own LLM provider.
Events charged:
- Actor start (based on memory used, charged per 128 MB unit)
- Running time (charged every 5 minutes, per 128 MB unit)
- Query answered (depends on the model used, not charged if you provide your own API key for LLM provider)
When you use your own LLM provider API key, running the MCP Client for 1 hour with 128 MB memory costs approximately $0.06. With the Apify Free tier (no credit card required 💳), you can run the MCP Client for 80 hours per month. Definitely enough to test your MCP server!
📖 How it works#how-it-works
Browser ← (SSE) → Tester MCP Client ← (HTTP streamable or SSE) → MCP Server
We create this chain to keep any custom bridging logic inside the Tester MCP Client, while leaving the main MCP Server unchanged. The browser uses SSE to communicate with the Tester MCP Client, and the Tester MCP Client relies on HTTP streamable or SSE to talk to the MCP Server. This separates extra client-side logic from the core server, making it easier to maintain and debug.
- Navigate to
https://tester-mcp-client.apify.actor?token=YOUR-API-TOKEN(or http://localhost:3000 if you are running it locally). - Files
index.htmlandclient.jsare served from thepublic/directory. - Browser opens SSE stream via
GET /sse. - The user's query is sent with
POST /message. - Query processing:
- Calls Large Language Model.
- Optionally calls tools if required using
- For each result chunk,
sseEmit(role, content)
Local development#local-development
The Tester MCP Client Actor is open source and available on GitHub, allowing you to modify and develop it as needed.
Download the source code:
git clone https://github.com/apify/tester-mcp-client.gitcd tester-mcp-client
Install the dependencies:
npm install
Create a .env file with the following content (refer to the .env.example file for guidance):
APIFY_TOKEN=YOUR_APIFY_TOKENLLM_PROVIDER_API_KEY=YOUR_API_KEY
Default values for settings such as mcpUrl , systemPrompt , and others are defined in the const.ts file. You can adjust these as needed for your development.
Run the client locally
$npm start
Navigate to http://localhost:3000 in your browser to interact with the MCP server.
Happy chatting with Apify Actors!
ⓘ Limitations and feedback#limitations-and-feedback
The client does not support all MCP features, such as Prompts and Resource.
References#references
- Model Context Protocol
- Apify MCP Server
- Apify MCP Server
- Pay-per-event pricing model
- What are AI Agents?
- What is MCP and why does it matter?
- How to use MCP with Apify Actors
- Apify MCP Server Tutorial: Integrate 5,000+ Apify Actors and Agents Into Claude
On this page
Share Actor:
Related articles
Build and deploy MCP servers in minutes with a TypeScript templateRead moreBest MCP servers for developersRead moreHow to use MCP with Apify ActorsRead more
Tester MCP Client Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Tester MCP Client's Information
- Category
- Development Tools
- Updated
- 14 days ago
Similar MCP Servers like Tester MCP Client
Explore related MCPs that share similar capabilities and solve comparable challenges
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
Framelink Figma MCP Server
by GLips
Provides Figma layout and styling information to AI coding agents, enabling one‑shot implementation of designs in any framework.
GitMCP
by idosal
Provides a remote Model Context Protocol server that transforms any public GitHub repository into an up‑to‑date documentation hub, enabling AI assistants to fetch live code and docs, dramatically reducing hallucinations.