Borrowing it
Nothing to install: this file belongs to vuluu2k/webcake-landing-mcp. 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/vuluu2k/webcake-landing-mcp/main/.claude/skills/connector-directory/SKILL.mdgit clone --depth 1 https://github.com/vuluu2k/webcake-landing-mcpWrote 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/vuluu2k/webcake-landing-mcp/connector-directory)<a href="https://agentmods.dev/skills/vuluu2k/webcake-landing-mcp/connector-directory"><img src="https://agentmods.dev/badge/skills/vuluu2k/webcake-landing-mcp/connector-directory/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/vuluu2k/webcake-landing-mcp/connector-directory"><img src="https://agentmods.dev/badge/skills/vuluu2k/webcake-landing-mcp/connector-directory.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 | $0.00103 | $0.01250 |
| Opus 5 | $0.00051 | $0.00625 |
| Sonnet 5 | $0.00021 | $0.00250 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
connector-directory 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 11d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
connector-directory — publish to Claude & ChatGPT connector stores
How to take this MCP server from "installable" to "listed in the official connector/app directories of Claude and ChatGPT." The concrete, resumable task list lives in docs/connector-directory-plan.md — read it before doing work.
The three systems are SEPARATE (do not conflate)
| System | What it is | How this repo reaches it | Gets you into Claude/ChatGPT store? |
|---|---|---|---|
npm webcake-landing-mcp |
stdio package | npm publish (CI auto-release.yml) |
❌ local installs only |
MCP Registry io.github.vuluu2k/webcake-landing-mcp |
neutral metadata catalog | server.json + mcp-publisher publish (see [[mcp-registry-publishing]]) |
❌ independent catalog |
| Claude Directory / ChatGPT App Directory | each vendor's in-product store | host a remote MCP URL + submit a form + pass review | ✅ this skill |
Publishing to npm or the MCP Registry does not propagate to the vendor stores. They are submitted and reviewed separately.
Key mental model: nobody gives you a deploy port
Claude/ChatGPT do not host your code. You run the server (already deployed at https://mcp.toolvn.io.vn/mcp via serve mode — see src/http.ts); the platforms connect into your public HTTPS /mcp URL. "Deploy" = your infra, not theirs.
Two levels of "being a connector"
- Level A — self-serve add-by-URL (works TODAY, no submission): anyone pastes
https://mcp.toolvn.io.vn/mcp(or...?jwt=<WEBCAKE_JWT>for per-user auth) into Settings → Connectors → Add custom connector. Claude (Pro/Team/Enterprise + Desktop) and ChatGPT (Business/Enterprise/Edu, Developer mode). No OAuth strictly required — the?jwt=query path in src/http.tsapplyQueryAuthexists for the claude.ai dialog that can't set headers. Downside: only people with the URL can add it. - Level B — official directory listing (form + review): appears in the built-in connector/app list for everyone. Requires OAuth 2.1 (Claude) + metadata + review.
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.
- 11d ago First seen · 72 lines · 103 tokens per session scan A 77eff1a78dac
connector-directory is a skill published in the GitHub repository vuluu2k/webcake-landing-mcp (5 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 1,250 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…