tf2-wiki-mcp: Instructions file for Claude Code

CLAUDE.md

tf2-wiki-mcp CLAUDE.md is an instructions file for Claude Code from yusufaf/tf2-wiki-mcp. It costs 1,134 tokens per session, scanned A, original, MIT.

A repository instruction file for a Team Fortress Wiki MCP server, which lets AI tools look up game facts such as weapon statistics, loadouts, cosmetics, and patch information.

In plain words
What is it for?
Guiding development, testing, and maintenance of the Python server, its wiki client, search and page tools, and Team Fortress-specific lookup tools.
Why use it?
It helps agents use the wiki server correctly and test offline code separately from tests that contact the real wiki.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is yusufaf/tf2-wiki-mcp's own configuration. It tells Claude Code how to work on tf2-wiki-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 tf2-wiki-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yusufaf/tf2-wiki-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/yusufaf/tf2-wiki-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yusufaf/tf2-wiki-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 tf2-wiki-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yusufaf/tf2-wiki-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/yusufaf/tf2-wiki-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yusufaf/tf2-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yusufaf/tf2-wiki-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.

agentmods 80×15 button for tf2-wiki-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yusufaf/tf2-wiki-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yusufaf/tf2-wiki-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,134 This file is loaded in full into every session.
When invoked 1,134 The same file — it is already loaded in full.
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 $0.01134 $0.01134
Opus 5.5 $0.00454 $0.00454
Sonnet 5.5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 18d ago against content hash bd8b99cd5102, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tf2-wiki-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 18d 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.md · 56 lines

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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A FastMCP stdio server (~500 lines of Python) exposing the Team Fortress Wiki to LLM clients, so a model stops guessing at weapon stats and patch notes. Published to PyPI and run via uvx tf2-wiki-mcp.

Unofficial fan tooling — not affiliated with Valve or the wiki's contributors. Keep that disclaimer in the README.

Commands

uv sync                  # install, including dev group
uv run pytest            # offline tests (parsers + server construction)
uv run pytest --live     # also hits the real wiki
uv run tf2-wiki-mcp      # run the stdio server directly

Anything marked @pytest.mark.live is skipped unless --live is passed. The offline suite must stay network-free.

Layout

src/tf2_wiki_mcp/
  server.py            # build_server() -> FastMCP; INSTRUCTIONS; resource + prompts
  client.py            # WikiClient — async httpx wrapper over MediaWiki api.php
  tools/generic.py     # search_wiki, get_page, get_page_summary, get_page_sections, get_recent_changes
  tools/tf2.py         # get_weapon_stats, list_class_loadout, get_cosmetic, list_event_items, get_patch_notes
  parsers/infobox.py   # wikitext template -> dict of params
  parsers/weapon.py    # infobox params -> structured weapon stats

build_server() instantiates one shared WikiClient and passes it into each module's register(mcp, client). Tools take the client by injection rather than reaching for a global, which is what lets tests build a server without opening a connection.

Architecture

Two tool tiers, deliberately. tools/generic.py is a thin MediaWiki passthrough — it works for any page and never assumes TF2 structure. tools/tf2.py is domain-specific and returns parsed data. When the wiki changes its templates, generic tools keep working and only the TF2 tier breaks. Put anything schema-dependent in the TF2 tier; keep the generic tier dumb.

Read the full file on GitHub · 56 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. 18d ago Changed · +1 lines · +145 tokens per session bd8b99cd5102
  2. 2mo ago First seen · 55 lines · 989 tokens per session scan A 1a2aeb7b4687

Subscribe to this mod's changes

tf2-wiki-mcp CLAUDE.md is an instructions file published in the GitHub repository yusufaf/tf2-wiki-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 1,134 tokens to every session, about $0.0045 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.

Related

tf2-wiki-mcp CLAUDE.md compared with instructions from other repositories

tf2-wiki-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tf2-wiki-mcp CLAUDE.mdyusufaf/tf2-wiki-mcpInstructions file0yesterdayMITA1,134Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot