Server detail
Reliable web fetching MCP server with built-in retry logic, circuit breaker patterns, caching, and anti-bot bypass. Fetches URLs as raw HTML or clean markdown optimized for LLM consumption. Includes domain health checks and cache management tools.
An MCP server for retrieving web content and converting HTML into Markdown so language models can read, summarize and process pages more easily.
Collections featuring this MCP
Tool testing
fetch
Fetch a URL from the internet and convert HTML content into Markdown.
urlstring, required. The URL to fetch.max_lengthinteger, optional. Maximum returned characters; defaults to 5000.start_indexinteger, optional. Start extraction at a character index for chunked reads.rawboolean, optional. Whether to return the raw content without Markdown conversion.Connection modes
{
"mcpServers": {
"SteadyFetch": {
"url": "Generated by the provider after deployment"
}
}
}The Remote endpoint is generated by the provider after deployment; this page does not fabricate an unusable endpoint.
{
"mcpServers": {
"SteadyFetch": {
"command": "uvx",
"args": [
"mcp-server-fetch"
]
}
}
}Fetch can run directly with uvx mcp-server-fetch.
How to use
- 01Step 1
Review server capabilities and permission scope.
- 02Step 2
Copy the install command or JSON configuration.
- 03Step 3
Run a small connection test in your client.
- 04Step 4
Adopt it long term only after reviewing access and maintenance.
Discussions
Use this space to keep checking source information, usage experience and maintenance status.
Open source page