Borrowing it
Nothing to install: this file belongs to vantage-sh/vantage-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vantage-sh/vantage-mcp-server/main/.agents/skills/verify-vantage-mcp/SKILL.mdgit clone --depth 1 https://github.com/vantage-sh/vantage-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/vantage-sh/vantage-mcp-server/verify-vantage-mcp)<a href="https://agentmods.dev/skills/vantage-sh/vantage-mcp-server/verify-vantage-mcp"><img src="https://agentmods.dev/badge/skills/vantage-sh/vantage-mcp-server/verify-vantage-mcp/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/vantage-sh/vantage-mcp-server/verify-vantage-mcp"><img src="https://agentmods.dev/badge/skills/vantage-sh/vantage-mcp-server/verify-vantage-mcp.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 | $0.00040 | $0.03584 |
| Opus 5.5 | $0.00016 | $0.01434 |
| Sonnet 5.5 | $0.00008 | $0.00717 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade A, and why
verify-vantage-mcp scanned grade A with 0 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify the Vantage MCP server
The server has three surfaces a user touches:
| Surface | Entry point | Who uses it |
|---|---|---|
| Hosted Worker, Streamable HTTP | /mcp (legacy /sse) on wrangler dev locally, https://hosted-mcp-staging.vantage.sh/mcp on staging |
OAuth clients; API/service-token clients over bearer auth; agents over delegation headers |
| Hosted Worker, OAuth endpoints | /.well-known/*, /register, /authorize, /token, /callback |
Every OAuth MCP client before its first tool call |
| Local stdio | npm run local (src/local.ts) |
Self-hosted users with a Vantage API token |
Locally the Worker runs in one of two modes, and a run picks exactly one:
- oauth —
VANTAGE_MCP_TOKENis blank, so bearer requests use the OAuth provider, including direct API/service-token passthrough throughresolveExternalToken; Core validates these credentials on tool calls. Delegation-only MCP requests use the pre-router described in hosted tool calls. Development Auth0 settings arelocal-dummy, so browser login works up to the consent screen and stops at Allow Access. - token —
VANTAGE_MCP_TOKENis set, so/mcpand/sseskip OAuth and call Core with that token. OAuth endpoints are not served in this mode.
The full OAuth login (Auth0, /callback, /token, refresh) only works on staging. See features/oauth-staging-full-flow.md.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 43 B
- features/hosted-tool-calls.md 13 KB
- features/local-stdio.md 2.5 KB
- features/oauth-local-consent.md 4.7 KB
- features/oauth-staging-full-flow.md 6.4 KB
- features/README.md 3.5 KB
- scripts/auth-routing.ts 5.0 KB runs code
- scripts/helpers.test.ts 7.6 KB runs code
- scripts/mcp-client.ts 9.4 KB runs code
- scripts/mcp-smoke.ts 4.2 KB runs code
- scripts/oauth-consent.ts 9.9 KB runs code
- scripts/oauth-refresh.ts 4.6 KB runs code
- scripts/support.ts 7.4 KB runs code
- scripts/tsconfig.json 271 B
- scripts/verify.sh 8.3 KB runs code
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.
- 9d ago Changed · +13 lines de08f33f8a31
- 10d ago First seen · 146 lines · 40 tokens per session scan A 59cb4c3ca6ca
verify-vantage-mcp is a skill published in the GitHub repository vantage-sh/vantage-mcp-server (86 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 3,584 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…