Borrowing it
Nothing to install: this file belongs to lukleh/mcp-read-only-grafana. 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/lukleh/mcp-read-only-grafana/main/AGENTS.mdgit clone --depth 1 https://github.com/lukleh/mcp-read-only-grafanaWrote 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/lukleh/mcp-read-only-grafana/agents-md)<a href="https://agentmods.dev/instructions/lukleh/mcp-read-only-grafana/agents-md"><img src="https://agentmods.dev/badge/instructions/lukleh/mcp-read-only-grafana/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.
<a href="https://agentmods.dev/instructions/lukleh/mcp-read-only-grafana/agents-md"><img src="https://agentmods.dev/badge/instructions/lukleh/mcp-read-only-grafana/agents-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 | $0.03269 | $0.03269 |
| Opus 5.5 | $0.01308 | $0.01308 |
| Sonnet 5.5 | $0.00654 | $0.00654 |
| Haiku 4.5 | $0.00327 | $0.00327 |
Grade A, and why
mcp-read-only-grafana 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 1mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Overview
MCP Read-Only Grafana Server provides a read-only default command plus a separate write-capable command for Grafana via the Model Context Protocol (MCP). It authenticates with a Grafana API key (preferred) or a deprecated browser session cookie, and supports multiple Grafana connections simultaneously.
Project Structure & Module Organization
src/mcp_read_only_grafana/server.py boots the MCP server, runtime-path helpers, and root management subcommands. The Grafana API client lives in grafana_connector.py; connection parsing and credential precedence live in config.py; runtime path resolution lives in runtime_paths.py; typed errors are in exceptions.py; and validation helpers are in validation.py. Tool registration is split by domain under src/mcp_read_only_grafana/tools/ (dashboard, datasource, alert, user, admin, plus core helpers). Tests live in tests/, and connections.schema.json plus connections.yaml.sample document the config surface.
Runtime Config Location
- The live runtime Grafana config file is:
~/.config/lukleh/mcp-read-only-grafana/connections.yaml - The checked-in
connections.yaml.samplefile is documentation/source material only. --write-sample-configwrites the sample into the resolved runtime config directory.--config-dir /path/to/config-dirchanges the live config file location to:/path/to/config-dir/connections.yaml
When updating config-location documentation, keep these aligned:
Build, Test, and Development Commands
uv sync --extra devinstalls runtime and development dependencies.uv run mcp-read-only-grafanaruns the read-only server manually for testing.uv run mcp-grafana-writeruns the separate write-capable command.uv run mcp-read-only-grafana --print-pathsshows the resolved config, state, and cache locations.uv run mcp-read-only-grafana --write-sample-configwrites the default config files; add--overwriteonly when replacing them intentionally.uv run mcp-read-only-grafana validate-configvalidatesconnections.yamlagainst the packaged schema.uv run mcp-read-only-grafana test-connectionchecks all configured connections; pass a connection name to scope it.uv run pytest -qruns the full test suite.uv run pytest tests/test_server.py -qis a fast focused iteration loop.uv run pytest -v -m "not integration"runs only unit tests, which need no credentials.uv run pytest tests/test_integration_all_endpoints.py -v -m integrationruns the integration suite, which requires Grafana credentials.RUN_WRITE_TESTS=1 uv run pytest tests/test_integration_all_endpoints.py -v -m integrationruns the write-capable integration coverage.uv run pytest tests/test_integration_all_endpoints.py::TestAlertingProvisioningAPI -vruns one integration category.uv run ruff check src/mcp_read_only_grafana testslints anduv run ty checktype-checkssrc/.
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.
- 1mo ago Changed · +5 lines · +151 tokens per session dcb288158903
- 1mo ago Changed · +160 lines · +2,254 tokens per session 4e91ce565ed7
- 1mo ago First seen · 44 lines · 864 tokens per session scan A fd85a984953f
mcp-read-only-grafana AGENTS.md is an instructions file published in the GitHub repository lukleh/mcp-read-only-grafana (3 stars, last pushed 5d ago), licensed MIT. It adds 3,269 tokens to every session, about $0.0131 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.