webcake-landing-mcp: Agent for Claude Code

.claude/agents/mcp-tool-author.md

mcp-tool-author is an agent for Claude Code from vuluu2k/webcake-landing-mcp. It costs 81 tokens per session (742 once invoked), scanned A, original, MIT.

A set of instructions for adding or changing MCP tools in the webcake-landing server. MCP tools are small actions an AI agent can call, such as retrieving data or saving a result.

In plain words
What is it for?
Use it when adding a tool, changing its inputs or behavior, or exposing a new backend request. It covers tool definitions, validation, dry runs, redaction, and backend configuration checks.
Why use it?
It helps developers follow the server's existing structure, input rules, safety checks, and registration process when exposing backend functions to an agent.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is vuluu2k/webcake-landing-mcp's own configuration. It tells Claude Code how to work on webcake-landing-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything webcake-landing-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vuluu2k/webcake-landing-mcp/main/.claude/agents/mcp-tool-author.md
Clone the repo
git clone --depth 1 https://github.com/vuluu2k/webcake-landing-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for mcp-tool-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author/github.svg)](https://agentmods.dev/agents/vuluu2k/webcake-landing-mcp/mcp-tool-author)
Your own site
<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.

agentmods 80×15 button for mcp-tool-author

Your own site · 80×15
<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>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash ee1b3d303531, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/agents/mcp-tool-author.md · 42 lines

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 a build…Redacted helper that masks the JWT. Only hit the network when dry_run === false.
  • Always domain.validate(source) before a create/update tool persists; bail with the errors if invalid. Use domain.coerce(source) to accept object-or-JSON-string.
  • New HTTP endpoints go in src/persistence/webcake-client.ts (add the URL constant, an authHeaders-based call, and a build…Redacted preview), never inline in a tool module.
  • Logging is console.error only (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: the INSTRUCTIONS string in src/domains/landing/instructions.ts (the closing "Tools:" line), the group file's header comment, and the tool lists in docs/tools.md(+.vi) + the README.md at-a-glance table + .claude/skills/webcake-landing/SKILL.md.

Read the full file on GitHub · 42 lines

Changes

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.

  1. 11d ago First seen · 42 lines · 81 tokens per session scan A ee1b3d303531

Subscribe to this mod's changes

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.