Tester MCP Client
Pricing
Pay per event
Tester MCP Client
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
11
Total users
293
Monthly users
208
Runs succeeded
0%
Last modified
2 days ago
MCP Server Sent Events (SSE) URL
mcpSseUrlstringOptional
MCP Server Sent Events (SSE) URL for receiving updates from the server.
Make sure that URL path ends with /sse
MCP Server URL
mcpUrlstringRequired
URL of the MCP Server for updates. Use SSEClientTransport if the URL ends with /sse; otherwise, use HttpStreamableClientTransport.
Default value of this property is "https://actors-mcp-server.apify.actor/sse?enableAddingActors=true"
MCP transport type specification
mcpTransportTypeEnumOptional
This setting helps you to override the MCP transport layer if required. Use SSEClientTransport for Server Sent Events (2024-11-05) or HttpStreamableClientTransport for JSON Response Streamable HTTP (2025-03-26).
Value options:
"sse": string"http-streamable-json-response": stringDefault value of this property is "sse"
HTTP headers
headersobjectOptional
HTTP headers to be sent with the request to the MCP server. If you are using Apify's MCP server, headers are NOT required
System prompt
systemPromptstringOptional
System prompt for the Claude model
Default value of this property is "You are a helpful Apify assistant with 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 discover Actors, find details, and include them among tools for later execution.\n\nModel Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs.\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 is used and with which parameters.\nNever call an Actor unless it is required by the user!\nAfter receiving an Actor's 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 a URL to the Actor whenever possible, like `[apify/rag-web-browser](https://apify.com/apify/rag-web-browser)`.\nREMEMBER: Always limit the number of results returned from Actors.\nThere is always a parameter such as `maxResults=1`, `maxPage=1`, `maxCrawledPlacesPerSearch=1`. Keep it to the minimal value.\nOtherwise, Actor execution takes a long time and the result can be huge!\nAlways inform the user that calling an Actor might take some time.\n"
Anthropic Claude model (Anthropic is only supported provider now)
modelNameEnumRequired
Select a model to be used for selecting tools and generating text.
- Claude 3.7 Sonnet (latest) - the most intelligent model
- Claude 3.5 Haiku (latest) - a fastest model
Value options:
"claude-3-7-sonnet-latest": string"claude-3-5-haiku-latest": stringDefault value of this property is "claude-3-7-sonnet-latest"
LLM Provider API key (Anthropic is only supported provider now)
llmProviderApiKeystringOptional
API key for accessing a Large Language Model. If you provide your own API key, Actor will not charge for query answered event.
Maximum tokens for Claude response
modelMaxOutputTokensintegerOptional
Maximum number of tokens in the Claude response. The higher the number, the longer the response time
Default value of this property is 2048
