One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp Swap --scope user for --scope project to commit it to .mcp.json. Copy
Your client Claude Desktop ChatGPT Codex CLI Cursor VS Code / GitHub Copilot Gemini CLI Windsurf Cline Continue Goose Same endpoint everywhere; only the config key differs. The full list is in the descriptor . Claude Desktop · Settings → Connectors → Add custom connector
https://api.skillsregistry.net/mcp Paste the URL as the connector endpoint. No authentication. Copy
ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL
https://api.skillsregistry.net/mcp Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools. Copy
Codex CLI · ~/.codex/config.toml
[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp" Restart your client after editing the config. Copy
Cursor · .cursor/mcp.json (project) or ~/.cursor/mcp.json (global)
{
"mcpServers": {
"skillsregistry": {
"url": "https://api.skillsregistry.net/mcp"
}
}
} VS Code / GitHub Copilot · .vscode/mcp.json
{
"servers": {
"skillsregistry": {
"type": "http",
"url": "https://api.skillsregistry.net/mcp"
}
}
} Restart your client after editing the config. Copy
Gemini CLI · ~/.gemini/settings.json
{
"mcpServers": {
"skillsregistry": {
"httpUrl": "https://api.skillsregistry.net/mcp"
}
}
} Restart your client after editing the config. Copy
Windsurf · ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"skillsregistry": {
"serverUrl": "https://api.skillsregistry.net/mcp"
}
}
} Restart your client after editing the config. Copy
Cline · MCP Servers → Configure → cline_mcp_settings.json
{
"mcpServers": {
"skillsregistry": {
"type": "streamableHttp",
"url": "https://api.skillsregistry.net/mcp"
}
}
} Restart your client after editing the config. Copy
Continue · .continue/config.yaml
mcpServers:
- name: skillsregistry
type: streamable-http
url: https://api.skillsregistry.net/mcp Restart your client after editing the config. Copy
Goose · goose configure → Add Extension → Remote Extension (Streaming HTTP)
https://api.skillsregistry.net/mcp Name it skillsregistry; paste the URL when prompted. Copy
List every tool the server exposes — no auth, no SDK.
curl -s -X POST https://api.skillsregistry.net/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only. Copy
Resolve this skill directly via MCP tools/call get_skill.
curl -s -X POST https://api.skillsregistry.net/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_skill","arguments":{"slug":"harishrajan77-agentic-automl-mcp"}}}' Pass X-Tenant-Id to union a private overlay with the public catalog. Copy