INDIVIDUAL MCP TOOL

upload_packages

[PRIVATE UPLOAD] Push local primitive(s) into the author's PRIVATE workspace.

superagentskill.comnone authenticationAvailability not checked

Input schema

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.superagentskill-com]
url = "https://superagentskill.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "superagentskill-com": {
      "type": "http",
      "url": "https://superagentskill.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: superagentskill-com
Remote MCP URL: https://superagentskill.com/api/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": {
    "superagentskill-com": {
      "url": "https://superagentskill.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "superagentskill-com": {
      "type": "http",
      "url": "https://superagentskill.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "superagentskill-com",
  "transport": "streamable-http",
  "url": "https://superagentskill.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

overview — START HERE if unsure.
get_methodology — [UPGRADE] Orientation for the local-file upgrade flow.
review_skill — [UPGRADE] Score a local skill / playbook / soul / guardrail with the proprietary SuperAgentSkill engine.
review_skills_batch — [UPGRADE] Batch variant of `review_skill` — score up to 10 local files in ONE call, evaluated in parallel.
search_registry — [DISCOVER] PRIMARY discovery tool.
list_packages — [DISCOVER] Browse published primitives by `type`.
get_package — [DISCOVER] Fetch the full latest-version manifest of a primitive by slug: system_prompt, rules, examples, compatibility.
get_skill_trust — [DISCOVER] Public Trust Report for a primitive: lifetime / 30d / 7d success rate, p50/p95 latency, per-model heatmap, robustness findings (CVE-style) and composite trust_score (0-100).