← All MCP servers
MCP server directory

SteadyFetch

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.

Version:
hosted
Publisher:
intake-triage

Install

Generated from the server’s transport data — never hand-written. Placeholders in angle brackets are yours to fill.

Run it with its own identity, a budget you set, and every call audited — no local config to keep in sync.

Add to a connect0 project

You will sign in first, then land back on this page.

What it can do

As declared by the publisher

Tools · 5

  • cache_stats

    Get cache statistics — size and item count. ``` Useful for monitoring cache utilization and deciding when to clear. ```

  • check_domain

    Check the health status of a domain. ``` Returns the circuit breaker state: 'closed' (healthy), 'open' (failing), or 'half_open' (testing recovery). Use this before batch operations to avoid wasting time on domains that are down. Args: domain: The domain to check (e.g., 'example.com') ```

  • clear_cache

    Clear the entire fetch cache. ``` Use when you need fresh data and don't want to rely on cached results. ```

  • fetch_markdown

    Fetch a URL and return clean markdown text optimized for LLM consumption. ``` Same reliability as fetch_url but returns only the markdown content, stripping HTML, scripts, and noise. Best for when you need the page content for analysis, summarization, or data extraction. Args: url: The URL to fetch use_cache: Whether to use cached results (default: true) wait_for: CSS selector to wait for before capturing ```

  • fetch_url

    Fetch a URL with full reliability — retry, circuit breaker, cache, and anti-bot bypass. ``` Returns both raw HTML and clean markdown. Automatically retries on failure with exponential backoff, falls back to plain HTTP if browser fetch fails, and circuit-breaks domains that are consistently down. Args: url: The URL to fetch use_cache: Whether to use cached results (default: true, TTL 1 hour) js_render: Whether to render JavaScript (default: true, disable for speed) wait_for: CSS selector to wait for before capturing (e.g., '.results-loaded') ```