What is required to use the Web Cat API MCP server?
A Serper API key is required for search functionality. The server can be run via Docker using the provided image (`tmfrisinger/webcat:latest`).
@Kode-Rex
Basic information
The repo for the GPT webcat
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"webcat": {
"command": "docker",
"args": [
"run",
"-p",
"8000:8000",
"-e",
"SERPER_API_KEY=your_key",
"tmfrisinger/webcat:latest"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Web Cat API is a collection of Python-based APIs that includes a Model Context Protocol (MCP) server for web search and content extraction. It integrates with Serper.dev for search capabilities and uses the readability library to extract clean text from web pages, making it easy to feed web content into AI models.
Run the MCP server via Docker with docker run -p 8000:8000 -e SERPER_API_KEY=your_key tmfrisinger/webcat:latest. You can also set a custom port or configure rate limiting via environment variables.
A Serper API key is required for search functionality. The server can be run via Docker using the provided image (`tmfrisinger/webcat:latest`).
It supports both Server-Sent Events (SSE) streaming and RESTful endpoints.
The APIs are optimized for text and image content and may not accurately represent other multimedia or dynamic web content.
Set the environment variables `RATE_LIMIT_WINDOW` (default 60 seconds) and `RATE_LIMIT_MAX_REQUESTS` (default 10) when running the Docker container.
The latest Docker image is available as `tmfrisinger/webcat:latest` or versioned as `tmfrisinger/webcat:1.1.0`.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
Comments