Loading…
Hugging Face's official remote MCP server exposes models, datasets, Spaces, and Hub search to an agent.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 9 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The Hugging Face MCP Server MCP server exposes 4 tools, focused primarily on developer capabilities. It is categorised under AI/ML, maintained by Hugging Face, and published as an official Model Context Protocol integration. Its published description reads: "Hugging Face's official remote MCP server exposes models, datasets, Spaces, and Hub search to an agent". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Hugging Face MCP Server F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Unguarded destructive tools". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check Hugging Face MCP Server's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Hugging Face MCP Server to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://huggingface.co/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: hf_fs
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
Grammar; each token below is one args array element: ls URI [RecommendationRemove side-channel parameters; constrain tool inputs.
tool: hf_fs
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
pes, redirects, shell expansion, or multiple commands. {"type":"objecRecommendationAnnotate destructive tools and require human approval.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: hub_repo_search
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: hub_repo_details
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: hf_fs
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: hf_fs
An unusually long description is a common injection-padding tactic.
description length 3903 charsRecommendationKeep descriptions concise.
The official MCP server from Hugging Face gives an agent access to the Hub — searching models, datasets and Spaces, and reading their metadata — over a hosted remote endpoint.
https://huggingface.co/mcpReview which scopes a token grants before handing it to an agent.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.