‹ directory
87MCP SCORE
B

huggingface.co/mcp

https://huggingface.co/mcp
4 tools155 resources~4.8k tok/req100% annot.proto 2026-07-28
View public page ›
Xin
Raw JSON ›

Score by pillar

Security ·20100
Tool design ·18100
Schemas / desc ·1682
Reliability ·14100
Context-cost ·1259
Compliance ·12100
Coverage ·860

reliability: LOW (T1 single-shot, not credited - requires T3 >=24h)

Context-cost

4.8ktokens for tools/list

Paid on every request. Lean footprint for 4 tools.

ecosystem median ≈ 3k

MCP primitive coverage

the quality score covers tools
4
Tools
155
Resources
0
Prompts · none

Badge — paste it in your README

MCP Score badge — huggingface.co/mcp[![MCP Score](https://checkmcp.dev/badge/huggingface-co.svg?url=https%3A%2F%2Fhuggingface.co%2Fmcp)](https://checkmcp.dev/report?url=https%3A%2F%2Fhuggingface.co%2Fmcp)

About huggingface.co/mcp — FAQ

Is the huggingface.co/mcp MCP server safe to use?+
CheckMCP audited huggingface.co/mcp and gave it an MCP Score of 87/100 (grade B) — good — only minor issues. The audit runs an OWASP MCP Top 10 security pass (tool poisoning, hardcoded secrets, command injection, the lethal trifecta) against the live endpoint; see the per-pillar breakdown and the "why this score" attribution on this page, and re-audit anytime at checkmcp.dev.
What is the MCP Score of huggingface.co/mcp?+
huggingface.co/mcp scores 87/100 (grade B) on CheckMCP's vendor-neutral audit across six weighted pillars — security, tool design, schemas, context-cost, compliance and coverage — with reliability measured and shown but not yet credited.
How many tools does huggingface.co/mcp expose, and what is its context cost?+
huggingface.co/mcp exposes 4 tools, and its tools/list response costs roughly 4.8k tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was huggingface.co/mcp scored?+
By probing the live MCP endpoint (https://huggingface.co/mcp), inspecting its tools, schemas and protocol compliance, running an OWASP MCP Top 10 security pass, and measuring the token cost of tools/list — then attributing every penalty as measure → mechanism → effect. The methodology is open: checkmcp.dev/#methodology.