Server
Wraps the MCPSkills trust scoring API so you can vet MCP servers and npm packages before installing them directly from Claude or Cursor. Exposes tools like check_trust_score for 13 signal assessments across four dimensions (Alive, Legit, Solid, Usable), scan_safety for detecting prompt injection and credential theft patterns, and auto_gate for go/no-go decisions with reasoning. Free tier gets you trust tiers and dimension scores with a 10/day limit. Developer Pro unlocks full reports with all 15 signals in Skills Mode plus safety findings. Useful when you're browsing the MCP registry or evaluating third-party AI skills and want a second opinion backed by OpenSSF Scorecard data and attack pattern detection before you add something to your config.
- GitHub stars
- 1
- tools
- 9
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Jun 9, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
check_trust_scoreScore any GitHub repo, npm package, or registry URL. Returns trust tier, composite score, and 4 dimension scores.
Score any GitHub repo, npm package, or registry URL. Returns trust tier, composite score, and 4 dimension scores.
No parameter schema in public metadata yet.
scan_safetyFocused safety scan for AI skills. Checks for prompt injection, shell execution, network exfiltration, credential theft, and obfuscated payloads.
Focused safety scan for AI skills. Checks for prompt injection, shell execution, network exfiltration, credential theft, and obfuscated payloads.
No parameter schema in public metadata yet.
list_packagesBrowse curated, pre-scored skill packages organized by use case.
Browse curated, pre-scored skill packages organized by use case.
No parameter schema in public metadata yet.
get_badgeGenerate an SVG trust badge URL for your README.
Generate an SVG trust badge URL for your README.
No parameter schema in public metadata yet.
watch_repoStart monitoring a repo for trust score changes (requires API key).
Start monitoring a repo for trust score changes (requires API key).
No parameter schema in public metadata yet.
check_watchedRe-scan all watched repos for score or tier changes (requires API key).
Re-scan all watched repos for score or tier changes (requires API key).
No parameter schema in public metadata yet.
batch_checkScore up to 5 repos in a single call (Developer Pro or Team).
Score up to 5 repos in a single call (Developer Pro or Team).
No parameter schema in public metadata yet.
auto_gateGet a boolean go/no-go decision with reasoning.
Get a boolean go/no-go decision with reasoning.
No parameter schema in public metadata yet.
build_stackRecommend a vetted, pre-scored stack from MCP Skills' curated packages.
Recommend a vetted, pre-scored stack from MCP Skills' curated packages.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
MCPSKILLS_API_KEYsecretOptional Pro API key for higher rate limits and full reports.
Readme
@mcpskillsio/server
Use the MCPSkills pre-install trust layer from inside Claude Code, Cursor, or any MCP client.
13 standard signals (15 in Skills Mode) across 4 dimensions with safety scanning for prompt injection, credential theft, and supply chain attacks. Check install risk before an MCP server or AI skill reaches your agent.
Details
- Repository
- github.com/bebravebekind/mcpskills-server
- Website
- mcpskills.io
- Package
@mcpskillsio/server- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active