Borrowing it
Nothing to install: this file belongs to kud/mcp-lastfm. 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/kud/mcp-lastfm/main/CLAUDE.mdgit clone --depth 1 https://github.com/kud/mcp-lastfmWrote 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/instructions/kud/mcp-lastfm/claude-md)<a href="https://agentmods.dev/instructions/kud/mcp-lastfm/claude-md"><img src="https://agentmods.dev/badge/instructions/kud/mcp-lastfm/claude-md/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/instructions/kud/mcp-lastfm/claude-md"><img src="https://agentmods.dev/badge/instructions/kud/mcp-lastfm/claude-md.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 | $0.00482 | $0.00482 |
| Opus 5.5 | $0.00193 | $0.00193 |
| Sonnet 5.5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
mcp-lastfm CLAUDE.md 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 2mo 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.
What it actually says
mcp-lastfm
API Reference
Official API docs: https://www.last.fm/api/intro
Root endpoint: https://ws.audioscrobbler.com/2.0/ (method-based, not REST — every
call is a GET with method, api_key, and format=json query params).
This server is read-only and covers every method reachable with a plain api_key
(no signed api_sig, no session): discovery (artist.*, album.*, track.*,
tag.*, geo.*), aggregate charts (chart.*), a user's library (library.getArtists),
and personal listening data (user.*) — 41 tools in total. Write/authenticated
methods (scrobbling, track.love/unlove, *.addTags/removeTag, and every
auth.* method) require the signed shared-secret or session-key flow and are
deliberately out of scope.
Auth: MCP_LASTFM_API_KEY — a plain API key query param, no signing or session
required for these read methods.
Optional MCP_LASTFM_USERNAME sets a default account for the user.* tools: the
user argument is optional and resolves to args.user ?? MCP_LASTFM_USERNAME,
erroring only when neither is present. An explicit user always overrides the
default, so multi-user lookups of other public profiles still work.
Quirks worth knowing when touching src/index.ts:
- All numeric fields in Last.fm's JSON responses are strings (
"1234", not1234). - List responses wrap results in a resource-named object (e.g.
toptracks,topalbums,recenttracks) carrying an@attrkey with pagination metadata (page,perPage,totalPages,total). Search endpoints use OpenSearch-style keys instead (opensearch:totalResults, etc.). mbid(MusicBrainz ID) is often an empty string rather than absent.- Errors come back as HTTP 200 with
{ error: <code>, message: <string> }in the body —lastfmFetchchecks for this and treats it as a failure.
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.
- 2mo ago First seen · 36 lines · 482 tokens per session scan A 02514d1f9b6c
mcp-lastfm CLAUDE.md is an instructions file published in the GitHub repository kud/mcp-lastfm (0 stars, last pushed 4mo ago), licensed MIT. It adds 482 tokens to every session, about $0.0019 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 2026-08-31.
mcp-lastfm CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-lastfm CLAUDE.mdkud/mcp-lastfm | Instructions file | 0 | 4mo ago | MIT | A | 482 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |