Borrowing it
Nothing to install: this file belongs to ttpears/mediawiki-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/ttpears/mediawiki-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ttpears/mediawiki-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/instructions/ttpears/mediawiki-mcp/claude-md)<a href="https://agentmods.dev/instructions/ttpears/mediawiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ttpears/mediawiki-mcp/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/ttpears/mediawiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ttpears/mediawiki-mcp/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 | $0.00791 | $0.00791 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
mediawiki-mcp 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 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mediawiki-mcp
Multi-wiki MediaWiki MCP server. Published to npm as mediawiki-mcp.
Dual deployment — do not break either path
This server ships through two channels and both must keep working:
-
Claude Code plugin marketplace (ttpears/claude-plugins)
.claude-plugin/plugin.jsondeclaresmcpServers.mediawiki→npx -y mediawiki-mcp.- Entry point is
dist/index.js(thebininpackage.json) which runssrc/stdio.ts. - Config comes from env vars inherited from the Claude Code process.
- Changes here ship via npm publish (see
.github/workflows/release.yml); the marketplace pulls the new version automatically on nextnpxspawn. - Keep
plugin.jsonversionin sync withpackage.jsonversionwhen releasing.
-
LibreChat (https://www.librechat.ai/docs/features/mcp)
- Runs as a sidecar container via
docker-compose.override.yml, started withnpm run start:http→src/http-transport.ts. - LibreChat connects with
type: streamable-http,url: http://mediawiki-mcp:8009/mcp. - Reads a LibreChat session user header on every request (see commit 643aeae) for per-user attribution — don't regress this by caching user identity at session init.
- Host defaults to
0.0.0.0, portMEDIAWIKI_MCP_PORT(default 8009).
- Runs as a sidecar container via
Rule of thumb: any refactor to transport, auth, or tool registration must be exercised against both src/stdio.ts and src/http-transport.ts. Tool definitions live in src/tools/ and are shared — keep them transport-agnostic.
Architecture
src/index.ts— stdio entry (used by npx / plugin)src/http-transport.ts— streamable-HTTP entry (used by LibreChat)src/wiki-orchestrator.ts— routing + fan-out across registered wikissrc/wiki-registry.ts— env parsing (MEDIAWIKI_WIKIS, per-wiki creds)src/clients/rest-client.ts—/rest.php/v1/(MW 1.42+)src/clients/action-client.ts—/api.php+ bot-password login, shared cookie sessionsrc/tools/*.ts— tool implementations, registered viasrc/tools/index.ts
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 · 56 lines · 791 tokens per session scan A d6545123089a
mediawiki-mcp CLAUDE.md is an instructions file published in the GitHub repository ttpears/mediawiki-mcp (3 stars, last pushed 12d ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.