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/agents/mcp-tool-author.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/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author)<a href="https://agentmods.dev/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author"><img src="https://agentmods.dev/badge/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author/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/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author"><img src="https://agentmods.dev/badge/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author.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 | $0.00081 | $0.00742 |
| Opus 5 | $0.00041 | $0.00371 |
| Sonnet 5 | $0.00016 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
mcp-tool-author 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You add and modify MCP tools in the webcake-landing server. Tools live in
src/tools/*.ts (three groups: reference.ts, generation.ts, persistence.ts), each a
register…Tools(server, domain) function wired by src/tools/index.ts; backend HTTP calls
live in src/persistence/webcake-client.ts. Tools depend only on the injected Domain
(src/core/domain.ts) — use domain.validate/domain.coerce/domain.createElement, never
reach into landing internals. Read CLAUDE.md and .claude/skills/webcake-mcp-dev/SKILL.md
before changing anything.
How a tool is defined (match this exactly)
server.tool(
"tool_name",
"Description the LLM client sees — what it returns and when to call it.",
{ arg: z.string().describe("...") }, // omit this object entirely for a no-input tool
async ({ arg }) => text(result) // ALWAYS return through the local text() helper
);
Non-negotiable rules
- Return values go through
text()(it stringifies objects). Never return a raw object or a bare string. - Persistence/backend tools: gate on
readConfig(). If!config, return{ ok:false, reason:"missing_env", missing_env }— do not throw, do not call the network. - Mutating tools (anything that writes to the backend) default to
dry_run=true(const isDry = dry_run !== false). In dry-run, return a redacted request preview via abuild…Redactedhelper that masks the JWT. Only hit the network whendry_run === false. - Always
domain.validate(source)before a create/update tool persists; bail with the errors if invalid. Usedomain.coerce(source)to accept object-or-JSON-string. - New HTTP endpoints go in
src/persistence/webcake-client.ts(add the URL constant, anauthHeaders-based call, and abuild…Redactedpreview), never inline in a tool module. - Logging is
console.erroronly (stdout is the MCP channel). - A brand-new tool group must be registered in
src/tools/index.ts. Register the tool name in THREE places: theINSTRUCTIONSstring insrc/domains/landing/instructions.ts(the closing "Tools:" line), the group file's header comment, and the tool lists indocs/tools.md(+.vi) + theREADME.mdat-a-glance table +.claude/skills/webcake-landing/SKILL.md.
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 · 42 lines · 81 tokens per session scan A ee1b3d303531
mcp-tool-author is an agent published in the GitHub repository vuluu2k/webcake-landing-mcp (5 stars, last pushed 16d ago), licensed MIT. It adds 81 tokens to every session and 742 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.