mcp-vetter
Review a prospective MCP server for GoatCitadel adoption.
Skill by goatcitadel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/goatcitadel-mcp-vetter
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mcp-vetter
What's inside
- Skill name
mcp-vetter- Description
- Review a prospective MCP server for GoatCitadel adoption. Use when evaluating an MCP registry entry, GitHub repo, vendor docs page, or proposed MCP install so you can decide trust tier, auth posture, policy defaults, overlap risk, and whether the server should be adopted, quarantined, or rejected.
- License
- Apache-2.0
- Metadata
- version: 0.1.0
- Instructions
- 107 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# mcp-vetter Use this skill to judge whether an MCP server belongs in GoatCitadel before anyone installs or enables it. ## What This Skill Does - reviews the server against GoatCitadel trust posture - identifies auth model, transport shape, and likely side effects - checks overlap with existing native features, integrations, or MCP templates - recommends trust tier and default policy - returns a clear adoption verdict instead of vague pros/cons ## What This Skill Does Not Do - it does not install the server - it does not edit runtime config - it does not weaken policy defaults - it does not treat marketplace popularity as proof of safety ## Review Order 1. Confirm the source: - official vendor docs/repo - community repo - abandoned or unclear maintainer 2. Classify the transport: - stdio - HTTP / streamable HTTP - SSE 3. Classify auth: - none - token - OAuth2 - host-specific / unclear 4. Classify blast radius: - read-only docs or search - repo / file mutation - billing / customer data - browser automation - infrastructure / production control 5. Check for overlap: - does GoatCitadel already have a native feature for this? - does an existing MCP template already cover this? - would this duplicate a current skill or tool path? ## Default Heuristics - official, read-only docs MCP: - likely `trusted` - `redactionMode = basic` - first-use approval optional - repo, billing, browser, or customer-data MCP: - default `restricted` - `redactionMode = strict` for sensitive data - `requireFirstToolApproval = true` - unclear maintainer, weak docs, or dangerous tool mix: - `quarantined` or reject - if GoatCitadel already has a native path, prefer the native path unless the MCP server adds clear net-new value ## Output Contract Return these sections: ### Verdict - `adopt` - `conditional` - `quarantine` - `reject` ### Why - 2-5 concrete reasons tied to source, auth, tool surface, and overlap ### Recommended GoatCitadel Settings - trust tier - auth type - redaction mode - first-use approval - allow/block pattern ideas if obvious ### Operator Notes - what needs manual review - what would make the server safer - whether a native integration is better ## GoatCitadel References When relevant, align with: - `docs/MCP_SKILLS_CURATION.md` - `docs/SKILL_IMPORT_AND_TRUST_POLICY.md` ## Good Triggers - "vet this mcp" - "review this mcp server" - "is this mcp safe" - "should we add this mcp" - "evaluate this mcp server for GoatCitadel"
From goatcitadel/GoatCitadel, Apache-2.0.
More from goatcitadel/GoatCitadel
- 0.592score
sendclaw
goatcitadel
Setup your own "you@sendclaw.com" email here without your human -Autonomous email for AI agents.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
research
goatcitadel
Web research that searches, opens primary sources, and cites them.
SkillAFreshness: A★ 2Claude Code +9 - 0.573score
impeccable
goatcitadel
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
design-intelligence
goatcitadel
Build, extend, repair, or audit UI through a modular design decision system.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
opencode
goatcitadel
Delegate a scoped coding or review task to an operator-configured OpenCode CLI and inspect its reported changes in Chat.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
coding
goatcitadel
Implement, refactor, and fix code with minimal testable changes and deterministic verification.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
operations
goatcitadel
Diagnose runtime issues, manage incident response, verify policy posture, and execute safe operational changes with rollback planning.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
personal-assistant
goatcitadel
Summarize context, track action items, manage reminders, and support day-to-day operator workflows with prioritized next steps.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
goatcitadel-native-safe-self-improvement
goatcitadel
Capture corrections, log operational learnings, and draft review-gated improvement proposals for GoatCitadel guidance surfaces.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
citadel-mason
goatcitadel
Use when a user wants to create, customize, export, import, or review a GoatCitadel Citadel Blueprint.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
genie-npu-ir20
goatcitadel
Route text generation to the ir20 Windows ARM64 laptop node running GenieAPIService with OpenAI-compatible endpoints over Tailscale mesh.
SkillCFreshness: C★ 2Claude Code +9 - 0.448score
n8n-workflow-architect
goatcitadel
Use this Skill to design, refine, and troubleshoot n8n workflows based on natural-language requirements.
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 2
- Open issues
- 14
- Last commit (this folder)
- Mar 10, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 0.1.0
- License
- Apache-2.0
- Repository
- github.com/goatcitadel/GoatCitadel
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from goatcitadel
- 0.592score
sendclaw
goatcitadel
Setup your own "you@sendclaw.com" email here without your human -Autonomous email for AI agents.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
research
goatcitadel
Web research that searches, opens primary sources, and cites them.
SkillAFreshness: A★ 2Claude Code +9 - 0.573score
impeccable
goatcitadel
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…
SkillAFreshness: A★ 2Claude Code +9 - 0.557score
design-intelligence
goatcitadel
Build, extend, repair, or audit UI through a modular design decision system.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
opencode
goatcitadel
Delegate a scoped coding or review task to an operator-configured OpenCode CLI and inspect its reported changes in Chat.
SkillBFreshness: B★ 2Claude Code +9 - 0.507score
operations
goatcitadel
Diagnose runtime issues, manage incident response, verify policy posture, and execute safe operational changes with rollback planning.
SkillCFreshness: C★ 2Claude Code +9
Cite this page
mcp-vetter skill. Agent Mart. https://agentmart.dev/skills/goatcitadel-mcp-vetter (last updated 2026-10-24)