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/zapi-mcp/copilot-instructionsgit clone --depth 1 https://github.com/shigechika/zapi-mcpWhat 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 | $0.02500 | $0.02500 |
| Opus 5 | $0.01250 | $0.01250 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
zapi-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 2d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository overview
zapi-mcp is an MCP (Model Context Protocol) server exposing the Zabbix API
(active problems, hosts, item values, a daily_brief morning-patrol
summary) to AI assistants over stdio transport. Built on the official
mcp Python SDK's FastMCP (zapi_mcp/server.py). The actual Zabbix HTTP
client (ZapiClient, auth, pagination) lives in the separate zapi-lib
package; zapi_mcp/client.py is only a backward-compatible re-export shim.
See CLAUDE.md for the authoritative command list and architecture notes —
read it before reviewing changes to server.py or categories.py.
Build & validate
uv sync --dev
uv run pytest -v # all tests
uv run ruff check . # lint
uv run ruff format --check . # format check
This mirrors .github/workflows/ci.yml: a lint job (ruff check +
ruff format --check) and a separate test job (pytest -v) on Python
3.10/3.12/3.13 on Linux, plus one Windows 3.12 job specifically to catch
stdio newline regressions (modelcontextprotocol/python-sdk#2433). Both
lint and test are real CI gates here — unlike some sibling MCP repos in this
family, don't assume lint is unenforced.
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. As of now this
codebase has no logging usage at all, and every print() call in
__main__.py sits in a branch that calls sys.exit() before mcp.run()
is reached — the --version branch, the missing-env-var check,
and the --check / --brief branches — so none of them ever run
concurrently with the live stdio server. Flag any new code path that adds a
print(), or a logger without an explicit stderr handler, that could
execute while mcp.run() is active — that would be a new failure mode, not a
fix to an existing one.
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.
- 2d ago First seen · 168 lines · 2,500 tokens per session scan A 0574f99f561f
zapi-mcp copilot-instructions.md is an instructions file published in the GitHub repository shigechika/zapi-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 2,500 tokens to every session, about $0.0125 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-read-only-grafana CLAUDE.md
Instructions for lukleh/mcp-read-only-grafana, covering claude.md, project overview, runtime config location, development commands and install dependencies.
mcp-read-only-grafana AGENTS.md
Instructions for lukleh/mcp-read-only-grafana, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
mcp-server-excel mcp-llm-guidance.instructions.md
Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
openrouter-mcp-multimodal 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).
ntfy-mcp-server AGENTS.md
Instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.