Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cyanheads/met-museum-mcp-server --skill security-passgit clone --depth 1 https://github.com/cyanheads/met-museum-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cyanheads/met-museum-mcp-server/security-pass)<a href="https://agentmods.dev/skills/cyanheads/met-museum-mcp-server/security-pass"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/security-pass/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cyanheads/met-museum-mcp-server/security-pass"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/security-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00118 | $0.05026 |
| Opus 5 | $0.00059 | $0.02513 |
| Sonnet 5 | $0.00024 | $0.01005 |
| Haiku 4.5 | $0.00012 | $0.00503 |
Grade A, and why
security-pass scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Smell:** `return { body: await fetch(url).then(r => r.text()) }` rendered directly in `format()`. Or: `description: \`Look up ${tenant.customLabel}\`` where `customLabel` is tenant-supplied. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -rnE "\b(exec|spawn|execSync|spawnSync)\b" src/ This is a copy
100% identical to security-pass — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
An MCP server is a new attack surface with unique properties — tool output feeds back into the LLM's context, scopes gate what the model can do on the user's behalf, and per-request state must stay tenant-scoped. This skill walks a server through eight axes shaped around what the server builder actually controls. Framework-level concerns (transport, JSON-RPC parsing, auto-correlation, error classification) are out of scope — mcp-ts-core handles those.
Read the code. Don't trust patterns from memory.
When to Use
- Before a release
- After adding or modifying a batch of handlers or services
- Periodically (quarterly-ish)
- User asks for a "security review", "audit", "hardening pass", or similar
Inputs
Gather before starting. Ask if unclear:
- Scope — whole server, specific module, or recent diff?
- Known concerns — anything the user already suspects?
- Deployment context — multi-tenant? public network? auth mode? (stdio / local-http / public-http behave differently)
- Severity floor — report all findings, or skip medium/low?
Steps
1. Build the map
Surface what you're auditing before diving in. Paths below assume the mcp-ts-core layout — adjust to your repo.
find src/mcp-server/tools/definitions -name "*.tool.ts" | sort
find src/mcp-server/resources/definitions -name "*.resource.ts" 2>/dev/null | sort
find src/mcp-server/prompts/definitions -name "*.prompt.ts" 2>/dev/null | sort
find src/services -maxdepth 1 -mindepth 1 -type d | sort
Note: tool / resource / prompt counts, auth mode, storage provider, upstream APIs, which tools have destructiveHint, which handlers request a consent round via ctx.requestInput, which services hold module-scope state, whether the server reads roots.
If transport is streamable HTTP or SSE, also capture:
- Bind address (
127.0.0.1for local, or0.0.0.0/ public interface?) - Origin allowlist (DNS rebinding mitigation) — configured, or wildcard / missing?
- Session ID source (framework CSPRNG, or builder-supplied?) and binding to auth identity
- Any unauthenticated routes (
/healthz,/sse, metadata endpoints) — do they leak tool lists or tenant hints? - MCP Authorization spec: if implemented, PKCE enforced, token audience (
aud) checked, resource indicators used
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 347 lines · 118 tokens per session scan A bdcf2da08d1c
security-pass is a skill published in the GitHub repository cyanheads/met-museum-mcp-server (4 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 5,026 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). It is 100% identical to security-pass, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
observations
List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.
wtf-happened
Retrieve a distilled timeline of the current troubleshooting incident and generate a runbook skeleton. Returns a concise summary by default, or the full untruncated timeline on request.
wtf-now
Add a manual observation to the WTF flight recorder journal. The entry is stored as a crafted (intentional) record. Classification of the entry's action type is handled by the background classifier — do not attempt to infer it here.
wtf
Launch the WTF flight recorder for a new troubleshooting incident. Archives any prior incident, prompts for an optional title, then puts Claude into flight recorder mode where significant observations, theories, and corrective actions are journaled automatically.
bun-runtime-http
Covers Bun.serve, HTTP server configuration, routing, streaming responses, WebSockets, TLS/SSL, and middleware with Bun's native APIs.
bun-snippets-cli
CLI snippets and command-line automation recipes with Bun.