Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/pipeworx-io/mcp-crawlbaseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/pipeworx-io/mcp-crawlbase/crawlbase)<a href="https://agentmods.dev/mcp/pipeworx-io/mcp-crawlbase/crawlbase"><img src="https://agentmods.dev/badge/mcp/pipeworx-io/mcp-crawlbase/crawlbase.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
crawlbase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"crawlbase": {
"url": "https://gateway.pipeworx.io/crawlbase/mcp",
"type": "streamable-http"
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 6 lines scan A 1e648bd62d70
crawlbase is an MCP server published in the GitHub repository pipeworx-io/mcp-crawlbase (0 stars, last pushed 11d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
firecrawl
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web. Remote server at gateway.pipeworx.io.
scrapingdog
Scrapingdog MCP — wraps Scrapingdog (scrapingdog.com), a proxy-based web. Remote server at gateway.pipeworx.io.
decodo
Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly. Remote server at gateway.pipeworx.io.
bright-data
Bright Data MCP — Bright Data Web Unlocker + SERP API (brightdata.com). Remote server at gateway.pipeworx.io.
wayback
Internet Archive Wayback Machine MCP. Remote server at gateway.pipeworx.io.
oxylabs
Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io). Remote server at gateway.pipeworx.io.