Koskamo

Agent Skill & Config Security Audit MCP

A security scanner for AI agent skills and config files that detects hidden Unicode instructions, prompt injection, exfiltration commands, and over-broad permissions. It performs static analysis on files like SKILL.md and .mcp.json to identify risks before installation.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Agent Skill & Config Security Audit MCP logo, by tylerscomic-labCommunity listingStreamable HTTPOAuth sign-inEndpoint checked 2026-11-07Published by tylerscomic-lab
You need:API key from MCPize
MCP endpoint (Streamable HTTP)
https://agent-skill-audit-mcp.mcpize.run/mcp
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Scan SKILL.md and CLAUDE.md for hidden Unicode instructions
  • Audit .mcp.json for risky agent configurations
  • Detect prompt injection and exfiltration commands
  • Reveal and decode invisible characters in text

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.tylerscomic-lab/agent-skill-audit-mcp@1.0.0Source repository
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
348 ms
95th percentile latency
348 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 348 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agent-skill-config-security-audit-mcp https://agent-skill-audit-mcp.mcpize.run/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agent-skill-config-security-audit-mcp --url https://agent-skill-audit-mcp.mcpize.run/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-skill-config-security-audit-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-skill-config-security-audit-mcp": {
      "url": "https://agent-skill-audit-mcp.mcpize.run/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-skill-config-security-audit-mcp": {
      "type": "streamableHttp",
      "url": "https://agent-skill-audit-mcp.mcpize.run/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-skill-config-security-audit-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-skill-config-security-audit-mcp": {
      "type": "http",
      "url": "https://agent-skill-audit-mcp.mcpize.run/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agent-skill-config-security-audit-mcp https://agent-skill-audit-mcp.mcpize.run/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://agent-skill-audit-mcp.mcpize.run/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agent-skill-config-security-audit-mcp": {
      "serverUrl": "https://agent-skill-audit-mcp.mcpize.run/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Skill & Config Security Audit MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,787