observability-mcp AGENTS.md

observability-mcp AGENTS.md is an instructions file for Codex, OpenCode from sandraschi/observability-mcp. It costs 322 tokens per session, scanned A, original, MIT.

Project instructions for observability-mcp, a service that connects an AI coding agent to Grafana, Prometheus, and Loki monitoring systems. They document how the service starts, communicates, and is tested.

In plain words
What is it for?
They help start, install, test, and serve the monitoring control plane, which is a service for viewing metrics, dashboards, and logs.
Why use it?
They give an agent the repository's required commands, ports, standards, and important files instead of making it discover them from scratch.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/sandraschi/observability-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/observability-mcp

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.

agentmods badge for observability-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/observability-mcp/agents-md.svg)](https://agentmods.dev/instructions/sandraschi/observability-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/observability-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/observability-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 322 This file is loaded in full into every session.
When invoked 322 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00322 $0.00322
Opus 5 $0.00161 $0.00161
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 3d ago against content hash ed9f0e459d8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

observability-mcp 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 3d 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 · 39 lines

What it actually says

observability-mcp — Agent Guide

FastMCP 3.3+ control plane for fleet Grafana, Prometheus, and Loki (not a second PLG stack).

Entry points

  • just start — backend 12007 + Vite 12008
  • uv run observability-mcpobservability_mcp.cli:main (stdio or HTTP via MCP_TRANSPORT=http)

Ports

Service Port
Backend (MCP HTTP) 12007
Frontend (Vite) 12008
Process /metrics 12009
Unified Grafana / Prometheus / Loki 12000 / 12001 / 12002

Standards

  • Structured tool responses (success, message, domain fields)
  • Dual transport: stdio (IDE) + composite ASGI HTTP (/mcp, /api/*, /docs)
  • Fleet standards: mcp-central-docs
  • Install: mcp-central-docs/standards/AGENT_INSTALL_REFERENCE.md

Key files

  • README.md, INSTALL.md, CHANGELOG.md, llms.txt
  • docs/PRD.md, docs/FASTMCP_STATUS.md
  • mcp-central-docs/monitoring/MONITORING_CURRENT_SETUP.md

Quick ref

just install
just test
just serve
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. 3d ago First seen · 39 lines · 322 tokens per session scan A ed9f0e459d8d

Subscribe to this mod's changes

observability-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/observability-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 322 tokens to every session, about $0.0016 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.