What is mcp-for-kibana AGENTS.md?

Repository instructions for mcp-for-kibana, a server that lets AI assistants use selected Kibana tools. Kibana is a web interface for exploring data stored in Elasticsearch.

They guide setup, checks, live-stack testing, contract tests, end-to-end replay tests, and the project's Definition of Done.

They point the assistant to the project's authoritative design documents, commands, tests, and rules before it changes code.

How pedro-angel/mcp-for-kibana configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pedro-angel/mcp-for-kibana. 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/pedro-angel/mcp-for-kibana/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pedro-angel/mcp-for-kibana

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pedro-angel/mcp-for-kibana/agents-md/github.svg)](https://agentmods.dev/instructions/pedro-angel/mcp-for-kibana/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pedro-angel/mcp-for-kibana/agents-md"><img src="https://agentmods.dev/badge/instructions/pedro-angel/mcp-for-kibana/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pedro-angel/mcp-for-kibana/agents-md"><img src="https://agentmods.dev/badge/instructions/pedro-angel/mcp-for-kibana/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 577 This file is loaded in full into every session.

When invoked 577 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.

Model	Per session	Once invoked
Fable 5.1	$0.00577	$0.00577
Opus 5	$0.00289	$0.00289
Sonnet 5	$0.00115	$0.00115
Haiku 4.5	$0.00058	$0.00058

Measured 10d ago against content hash 24c5c82875d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-for-kibana AGENTS.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 10d 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide

You are working on mcp-for-kibana: an MCP server exposing Kibana to LLMs through curated, tier-gated toolboxes over a hexagonal core. The durable source of truth is the regeneration corpus — start there, not in the code:

docs/spec/brief.md — what this is, values, non-goals.
docs/spec/design.md — load-bearing shape, system invariants.
docs/spec/decisions.md — settled decisions with evidence; supersede explicitly, never silently.
docs/spec/toolboxes/ — per-toolbox behavior contracts.
docs/spec/regeneration.md — rebuilding rules; what is authoritative when documents and code disagree.

Reference material: docs/tools.md (tool surface), docs/architecture.md (diagrams), docs/roadmap.md (open work, recorded deferrals).

Commands

make setup        # uv sync + git hooks (run once)
make check        # content gates: hooks + lint + audit + sast + unit + docs
scripts/stack.sh up && scripts/stack.sh seed   # live dev stack (seed after EVERY start)
make test-contract / test-e2e-replay           # live tiers
KIBANA_MCP_DOD_CYCLE_STACK=1 make dod          # full Definition-of-Done → VERDICT: GO

The full make dod includes the live-model tier, which needs a local LM Studio runtime with the reference model loaded (docs/e2e-setup.md); without it that criterion cannot go GO. CI's per-tier configs under .github/dod/ mark it n/a.

House rules

The DoD gate certifies completion, not you. No completion or release claim without VERDICT: GO at that exact tree; every change carries a CHANGELOG entry.
Never bypass hooks (--no-verify is prohibited); commits are Conventional Commits with a provenance trailer (hooks enforce both).
Additive is default-off; error text must name the fix; specs are reconciled onto shipped code in the same change-set.
Report numbers trace to committed run records — never hand-transcribe results into documents.
.env.local and ~/.lmstudio/mcp.json are user-owned: never written by tooling or agents.

Read the full file on GitHub · 47 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.

10d ago First seen · 47 lines · 577 tokens per session scan A 24c5c82875d6

Subscribe to this mod's changes

mcp-for-kibana AGENTS.md is an instructions file published in the GitHub repository pedro-angel/mcp-for-kibana (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 577 tokens to every session, about $0.0029 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.

LLM dashboards elasticsearch kibana mcp

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

mcp-for-kibana: Instructions file for Codex