# SteadyFetch

SteadyFetch retrieves web pages as HTML or clean Markdown, retries failed requests, and keeps cached results. Use it when an agent needs consistent URL access.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 8946 installs
- Author: intake-triage
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/intake-triage/steadyfetch
- Updated: 2026-03-31
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/steadyfetch

## What it does

SteadyFetch gives an agent tools for reading pages and checking site availability. `fetch_url` returns the source page together with Markdown, while `fetch_markdown` strips markup, scripts, and other page noise. Failed requests are retried, and a browser-fetch failure can fall back to plain HTTP.

The server tracks domain failures with a circuit breaker, so a repeatedly failing host can be kept out of a batch run. Use `check_domain` before collecting from several URLs, then inspect storage with `cache_stats`. `clear_cache` removes all stored fetch results when the next request must use fresh data. It runs through a remote MCP endpoint, so the endpoint must be reachable from the client.

## Requirements
- Remote server: `https://steadyfetch--intake-triage.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http steadyfetch https://steadyfetch--intake-triage.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add steadyfetch --url https://steadyfetch--intake-triage.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "steadyfetch": {
            "url": "https://steadyfetch--intake-triage.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "steadyfetch": {
            "type": "http",
            "url": "https://steadyfetch--intake-triage.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http steadyfetch https://steadyfetch--intake-triage.run.tools
```

## When to use it
- retrieve a page as HTML and Markdown
- prepare clean page text for agent analysis
- check a domain before a batch fetch
- retry a failed web request
- remove cached results before a fresh fetch

## Example prompts
- Fetch `https://example.com` and return the page as clean Markdown.
- Check the health of `example.com` before starting a batch fetch.
- Show the cache statistics, then clear the cache if the stored pages are stale.

## Similar
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs
- [AI Research Assistant](https://affpapa.org/en/nevibecode/mcp/ai-research-assistant.md) — MCP server · 10296 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
