SkillTriage

dev.mooraiPublished by moorai.devOfficial publisherv0.6.1Updated Nov 1, 2026

Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that statically scans npm, PyPI and GitHub packages, MCP client configs and agent skill files for risks before you install them.

What you can do
  • Scan a published npm, PyPI or GitHub package: download it, run static analysis, and for npm/PyPI add ten MCP pre-install checks, a reputation score and a known-compromised release check
  • Check a pasted MCP client config: report each npm or PyPI launch by position, how its version is pinned, compromised releases and static analysis of the launched code
  • Scan one agent skill or instruction file such as SKILL.md, AGENTS.md or tool.json with the same static analysis engine
  • Look up the public catalogue's published verdict for an npm or PyPI MCP server package, without downloading or scanning anything
When to use it
Useful when an assistant is about to add an MCP server, install a package, or adopt an agent skill and you want a quick risk check first. Also handy for auditing an existing MCP client config for unpinned or known-compromised launches.
Requirements
Remote streamable HTTP endpoint; no authentication, environment variables or headers declared. Network access to the endpoint is required, and calls are rate-limited per IP address.
Before you install
Package names, config contents and skill text are sent to a third-party service; the server states submitted text is not stored, only a hash, verdict and content-free findings. Static analysis only, so a clean result is not a guarantee of safety, and a missing catalogue verdict is not a clean result. Rate limits apply per IP address.

Installation

In SourceWeft

  1. Open SkillTriage in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.moorai%2Fskilltriage/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "skilltriage": {
      "type": "http",
      "url": "https://skilltriage.moorai.dev/mcp"
    }
  }
}

Tools

4

scan_package

Scan an MCP server or skill package

Download one published package and run static analysis on its code with MoorAI's open-source engine. npm and PyPI packages also get ten MCP pre-install checks on their registry metadata, a reputation score and a known-compromised release check. Static analysis only: the package is never installed and the server is never run. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), content-free findings (threat ids, categories, file paths, hashes; never file contents) and a permalink. The package name and version are sent to its registry. A completed analysis is reused for 24 hours; a new one can take a minute and runs one at a time.

Parametersrefrequired

scan_mcp_config

Check an MCP client config

Check a pasted MCP client config (.mcp.json, claude_desktop_config.json, mcp.json, Codex config.toml). Reports each npm or PyPI launch by its position and how its version is pinned (exact, @latest, a tag or range, none), flags releases on the known-compromised list, and runs static analysis over the text. Server names, package names, arguments, env and header values are never returned or stored; remove secrets before sending anyway. Static analysis only; nothing is run or fetched. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), the pinning advice and a permalink.

Parameterstextrequiredfilename

scan_skill

Scan an agent skill file

Scan one agent skill or instruction file (SKILL.md, AGENTS.md, a tool.json, any text file) with MoorAI's open-source engine. Static analysis only; nothing is run. The text is written to a temporary directory, scanned and deleted; only its hash, the verdict and content-free findings are kept. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), the findings and a permalink.

Parameterstextrequiredfilename

lookup_verdict

Look up a published MCP server verdict

Look up the verdict the public catalogue has published for an MCP server package on npm or PyPI. Returns found:false when the catalogue has no published verdict for that name; that is not a clean result. Nothing is downloaded or scanned. This request names the package to the server; to match without naming it, download /api/reputation-feed.json and match on your side.

Parametersnamerequiredversionecosystemrequired

Version history

1
  1. v0.6.1LatestNov 1, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.