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-huggingfaceWrote 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-huggingface/huggingface)<a href="https://agentmods.dev/mcp/pipeworx-io/mcp-huggingface/huggingface"><img src="https://agentmods.dev/badge/mcp/pipeworx-io/mcp-huggingface/huggingface/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/pipeworx-io/mcp-huggingface/huggingface"><img src="https://agentmods.dev/badge/mcp/pipeworx-io/mcp-huggingface/huggingface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
huggingface 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 9d 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
{
"huggingface": {
"url": "https://gateway.pipeworx.io/huggingface/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.
- 9d ago First seen · 6 lines scan A d9278cbdcacc
huggingface is an MCP server published in the GitHub repository pipeworx-io/mcp-huggingface (0 stars, last pushed 14d 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
dbpedia
DBpedia MCP — SPARQL + Lookup over Wikipedia-derived structured data. Remote server at gateway.pipeworx.io.
arcgis-loudoun
Loudoun County GIS — Loudoun County, Virginia open geospatial data (ArcGIS). Remote server at gateway.pipeworx.io.
prism-mcp
Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work. Runs locally from the prism-mcp-server npm package. Needs 1…
football-data
Football-Data.org MCP — soccer competitions, matches, standings. Remote server at gateway.pipeworx.io.
llm-observability-orchestration
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith. Remote server at langchain-core-langsmith-openai-8c02f9.getvda.ai.
structured-output-agent
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Verte. Remote server at fastmcp-instructor-72225f.getvda.ai.