Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/shigechika/keycloak-mcp/copilot-instructionsgit clone --depth 1 https://github.com/shigechika/keycloak-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/shigechika/keycloak-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/shigechika/keycloak-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/keycloak-mcp/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01932 | $0.01932 |
| Opus 5 | $0.00966 | $0.00966 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
keycloak-mcp copilot-instructions.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 5d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository overview
keycloak-mcp is an MCP (Model Context Protocol) server exposing the
KeyCloak Admin REST API — users, sessions, events, security settings —
to AI assistants over stdio transport. It authenticates as a Service
Account (Client Credentials Grant, keycloak_mcp/auth.py) and talks to
the Admin API via KeyCloakClient (keycloak_mcp/client.py). Built on
the official mcp Python SDK's FastMCP (keycloak_mcp/server.py).
See CLAUDE.md for the authoritative command list and architecture
notes — read it before reviewing changes to client.py, auth.py, or
server.py.
Build & validate
uv sync --dev
uv run ruff check .
uv run ruff format --check .
uv run pytest -v
This mirrors .github/workflows/ci.yml: a lint job (ruff check +
format check) and a test job matrixed over Python 3.10–3.14 on Ubuntu,
plus one Windows 3.12 job specifically to catch stdio newline
regressions (modelcontextprotocol/python-sdk#2433). Ruff does run
in CI here — don't hand-flag formatting/import-order issues it already
enforces; focus review comments on things CI can't catch.
What to focus review on in this repo
1. This is a stdio MCP server — stdout is a JSON-RPC channel, not a log
Any print() or library logging that writes to stdout instead of
stderr corrupts the protocol stream for the connected client. The
existing convention in server.py and __main__.py is to route
diagnostics to stderr explicitly (print(..., file=sys.stderr)) in
tool error paths (reset_passwords_batch, get_totp_users,
daily_brief). The one exception is __main__.py's _check_config(),
which prints a plain confirmation line to stdout on --check — that
path calls sys.exit() before mcp.run() ever starts, so it never
shares the stream with JSON-RPC traffic. Flag any new code path that
writes to stdout on the mcp.run(transport="stdio") side, or that lets
a dependency's default logging config leak through.
2. FastMCP already wraps tool returns — don't ask for manual envelope code
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.
- 5d ago First seen · 145 lines · 1,932 tokens per session scan A 19d188a0701c
keycloak-mcp copilot-instructions.md is an instructions file published in the GitHub repository shigechika/keycloak-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 1,932 tokens to every session, about $0.0097 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
mcp-production-kit CLAUDE.md
Claude Code instructions for Lumina-AI-studio/mcp-production-kit, covering what this is, hard rules, stack & commands and testing.
AIQuantificationTools AGENTS.md
AGENTS.md instructions for wqjuser/AIQuantificationTools, covering agents.md, agent skills, issue tracker, triage labels and domain docs.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).