AI & Machine Learning
skillsregistry.net
Provides a registry for discovering, evaluating, and composing AI skills with trust metrics.
ENDPOINT 1
https://api.skillsregistry.net/mcp
MCP server metadata
- Name
- skillsregistry
- Version
- 6.2.0
Known tools 5
get_skillFetch a single skill record by slug, including manifest + trust breakdown.
Inferred read-onlyget_trust_breakdownReturn the trust slice of a skill: `trustBreakdown` groups Circle-IR analyzer passes into six 0-100 dimensions (security, supply, quality, reliability, compliance, provenance) with an overall score and the Circle-IR tier (VERIFIED / PASSING / ADVISORY / FAILING / BLOCKED).
Inferred read-onlyresolve_compositionResolve a composition slug into its constituent skills with lineage + cascade trust impact.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"skillsregistry": {
"type": "http",
"url": "https://api.skillsregistry.net/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: skillsregistry
Remote MCP URL: https://api.skillsregistry.net/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"skillsregistry": {
"url": "https://api.skillsregistry.net/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"skillsregistry": {
"type": "http",
"url": "https://api.skillsregistry.net/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "skillsregistry",
"transport": "streamable-http",
"url": "https://api.skillsregistry.net/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.