SkillTriage MCP server
dev.moorai/skilltriagemoorai.devstreamable-httpv0.6.1Scanned
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 2 findings, 2 high
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the SkillTriage MCP server can do
The SkillTriage MCP server is published by moorai.dev, a domain the MCP Registry verified. It has 4 tools. It can create or change data (3 tools: scan_package, scan_mcp_config and scan_skill), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (scan_package).
The fixed checks matched 2 findings, 2 of them high severity (sensitive-path). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 0.6.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 3Claude Code: ask
scan_mcp_configCheck a pasted MCP client config (.mcp.json, claude_desktop_config.json, mcp.json, Codex config.toml).2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- High
The description refers to ".mcp.json" and "claude_desktop_config.json".
What this check looks forMatched text
description: "Check a pasted MCP client config (.mcp.json, claude_desktop_config.json, mcp.json,..."
- High
The input schema at properties.filename.description refers to ".mcp.json".
What this check looks forMatched text
inputSchema.properties.filename.description: "...name, ending in .json or .toml (default .mcp.json)"
Description, as the server wrote it 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.
Annotations the server declares
- title: Check an MCP config
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
scan_packageDownload one published package and run static analysis on its code with MoorAI's open-source engine.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Scan a package
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
scan_skillScan one agent skill or instruction file (SKILL.md, AGENTS.md, a tool.json, any text file) with MoorAI's open-source engine.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Scan a skill file
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
lookup_verdictLook up the verdict the public catalogue has published for an MCP server package on npm or PyPI.No findings
Why it is in this group
- The name "lookup_verdict" says "lookup": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Look up a verdict
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 15, 2026, 13:21 UTC, unchanged since Oct 31, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://skilltriage.moorai.dev/mcp: tools/list returned 4 tools to an anonymous client, including scan_package (write), scan_mcp_config (write), scan_skill (write)
Findings
Matches of fixed checks, with the text they matched.
- Highscan_mcp_config
The description refers to ".mcp.json" and "claude_desktop_config.json".
What this check looks forMatched text
description: "Check a pasted MCP client config (.mcp.json, claude_desktop_config.json, mcp.json,..."
- Highscan_mcp_config
The input schema at properties.filename.description refers to ".mcp.json".
What this check looks forMatched text
inputSchema.properties.filename.description: "...name, ending in .json or .toml (default .mcp.json)"
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.6.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http skilltriage https://skilltriage.moorai.dev/mcpclaude mcp add --transport http skilltriage https://skilltriage.moorai.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__skilltriage__lookup_verdict"
],
"ask": [
"mcp__skilltriage__scan_package",
"mcp__skilltriage__scan_mcp_config",
"mcp__skilltriage__scan_skill"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as skilltriage. Review it before you use it.
Capability tags behind 1 rule
- mcp__skilltriage__scan_package untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.moorai/skilltriage/verify?hash=afa9009eae6232d833b99c081efa7453912324d2c193eb56f83728f5d7e1d5ab" | jq -e '.changed == false'Pinned hash afa9009eae62, from Nov 13, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.moorai/skilltriage/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.moorai/skilltriage)Source: MCP Registry. Synced Oct 31, 2026, 19:17 UTC.
SkillTriage MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SkillTriage MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 2 findings (2 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SkillTriage MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SkillTriage MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the SkillTriage MCP server have?
- 4 tools: 3 write, 1 read. scan_package, scan_mcp_config, scan_skill and lookup_verdict.
Does the SkillTriage MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SkillTriage MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the SkillTriage MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.