Borrowing it
Nothing to install: this file belongs to UmutKDev/myanimelist-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/UmutKDev/myanimelist-mcp/main/.claude/skills/add-mcp-tool/SKILL.mdgit clone --depth 1 https://github.com/UmutKDev/myanimelist-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/umutkdev/myanimelist-mcp/add-mcp-tool)<a href="https://agentmods.dev/skills/umutkdev/myanimelist-mcp/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/umutkdev/myanimelist-mcp/add-mcp-tool/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/umutkdev/myanimelist-mcp/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/umutkdev/myanimelist-mcp/add-mcp-tool.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 | $0.00042 | $0.00659 |
| Opus 5 | $0.00021 | $0.00329 |
| Sonnet 5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
add-mcp-tool 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an MCP tool
Adding a tool touches several files in lockstep. Canonical read example: get_my_anime_list
(server.py:888). Skipping a step (especially test registration or the fields param) breaks
the tool or the test suite. Read the surrounding code before writing — match the house style.
Checklist
- MAL client method — add the endpoint call to
MALClientinmal_client.py:- Define a
*_FIELDSconstant and pass it asfields(mandatory — without it MAL returns near-empty nodes and dropslist_status). Nested selection uses brace syntax (e.g.authors{first_name,last_name}). - Clamp any
limitto MAL's page cap; route through the existing_request/pagination path so 403/429 retries and redirect-as-failure handling apply.
- Define a
- Server helpers — add pure
_compact_*(slim the raw MAL JSON) and_summarize_*(model-facing text) helpers inserver.py. Keep them pure and underscore-prefixed. - Tool function — add
@mcp.tool(annotations={…}, meta=ui_tool_meta()):- Hints: read →
readOnlyHint: True; write →readOnlyHint: False+destructiveHint: True+idempotentHint(True for update/PATCH, False for delete). async def, params typed withAnnotated[..., Field(...)]/Literal, long LLM-facing docstring documentingArgs:and the return shape.- Do all MAL I/O via
await _call_mal(lambda client: client.<method>(...))— never construct a client directly (this is the token-resolution + error-mapping + refresh-retry choke point).
- Hints: read →
- Return shape:
- Read tool →
return ui_result(view, data, summary)with aviewstring the UI understands. - Write tool /
analyze_taste→ return a plain dict/str with nometa=ui_tool_meta().
- Read tool →
- UI view (only if
viewis new) — add a view inui/src/views/, wire it inui/src/mcp/bridge.tsandui/src/mcp/types.ts, then rebuild the bundle (see therebuild-ui-bundleskill). - Tests — register the new tool name in
tests/test_ui.py(UI_TOOLSfor UI-backed tools,NON_UI_TOOLSotherwise), and add pure-helper unit tests (injecthttpx.MockTransportfor client behavior;monkeypatchserver._call_malfor tool behavior). - Verify:
uv run pytest.
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 First seen · 38 lines · 42 tokens per session scan A fe997c191bc5
add-mcp-tool is a skill published in the GitHub repository UmutKDev/myanimelist-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 659 once invoked, about $0.0002 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…