SkillTriage
Server Details
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The four tools target distinct inputs: a catalogue query by name, a pasted config, a published package, and a single skill file. The main risk is lookup_verdict versus scan_package, since both are about a package, but the descriptions clearly separate a cached verdict lookup from a fresh download-and-scan.
All names follow a clean snake_case verb_noun pattern (lookup_verdict, scan_mcp_config, scan_package, scan_skill). The shared 'scan_' prefix for the three analysis tools reinforces the distinction between them and the lookup tool.
Four tools is on the lean side but each covers a genuinely different artifact (verdict catalogue, config, package, skill). Nothing feels redundant or bloated for a triage-focused server.
The surface covers the core triage paths: checking an existing verdict, scanning a package, a config, and a skill file, with a clear verdict taxonomy and permalinks. Minor gaps include no batch/multi-package scan or an explicit tool to fetch the reputation feed, though agents can work around these.
Available Tools
4 toolslookup_verdictLook up a published MCP server verdictARead-onlyIdempotentInspect
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.
Inputs: name (required), ecosystem (required), version.
scan_mcp_configCheck an MCP client configARead-onlyIdempotentInspect
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.
Inputs: text (required), filename.
scan_packageScan an MCP server or skill packageARead-onlyIdempotentInspect
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.
Inputs: ref (required).
scan_skillScan an agent skill fileARead-onlyIdempotentInspect
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.
Inputs: text (required), filename.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Static MCP server scan: injection, secrets, tool poisoning. SARIF + rules catalog.
Related MCP Servers
- AlicenseAqualityBmaintenanceLocal-first security scanner for AI agent skills, plugins, hooks and MCP servers. Read-only, offline tools to scan a skill or MCP server before installing it, audit the installed setup and review proxy pins.598 npmMIT
- AlicenseAqualityBmaintenanceSecurity scanner for third-party AI agent-skill files: SKILL.md manifests, hooks, and bundled scripts, exposed via an MCP tool.185 npm3Apache 2.0
- AlicenseNot gradedqualityCmaintenanceScans MCP servers, AI agent skills, and plugins for 68+ malicious patterns including credential exfiltration, prompt injection, and code execution.5MIT
- AlicenseAqualityDmaintenanceSecurity scanner for AI agent packages that enables AI agents to audit MCP servers and packages for vulnerabilities, prompt injection, and supply chain attacks.588 npm3AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.