Grafana AI Marketplace is a collection of plugins and related configuration for using AI coding agents with Grafana observability workflows. It connects agents to Grafana through either a hosted Grafana Cloud MCP server or a locally run Grafana MCP service, and its catalogue add-ons provide those integrations.
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 skills add grafana/ai-marketplace --skill grafana-mcp-toolsgit clone --depth 1 https://github.com/grafana/ai-marketplaceWrote 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/skills/grafana/ai-marketplace/grafana-mcp-tools)<a href="https://agentmods.dev/skills/grafana/ai-marketplace/grafana-mcp-tools"><img src="https://agentmods.dev/badge/skills/grafana/ai-marketplace/grafana-mcp-tools/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/skills/grafana/ai-marketplace/grafana-mcp-tools"><img src="https://agentmods.dev/badge/skills/grafana/ai-marketplace/grafana-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01233 |
| Opus 5.5 | $0.00035 | $0.00493 |
| Sonnet 5.5 | $0.00017 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
grafana-mcp-tools 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grafana MCP Server
The open-source Grafana MCP server, mcp-grafana. It runs locally and connects to any Grafana 9.0+ instance, self-hosted or Grafana Cloud, with a service account token.
Prerequisites
The MCP server must already be installed. Don't try to install it yourself. If it isn't available, stop and tell the user to install it first.
Installation instructions, binaries, Docker images and Helm charts: github.com/grafana/mcp-grafana
Configuration
Environment variables
| Variable | Description |
|---|---|
GRAFANA_URL |
Grafana instance URL (default: http://localhost:3000) |
GRAFANA_SERVICE_ACCOUNT_TOKEN |
Service account token (recommended) |
GRAFANA_API_KEY |
API key (deprecated; use a service account token) |
GRAFANA_USERNAME + GRAFANA_PASSWORD |
Basic auth |
GRAFANA_ORG_ID |
Organization ID for multi-org setups |
GRAFANA_EXTRA_HEADERS |
JSON object with custom HTTP headers |
Setup steps
- Create a service account in Grafana with at least the Viewer role (Editor for write operations), and generate a token.
- Give the server the Grafana URL and the token. Claude Code asks for both when the plugin is enabled. Other agents read them from the
GRAFANA_URLandGRAFANA_SERVICE_ACCOUNT_TOKENenvironment variables; the plugin's README shows how. - The MCP server starts when your agent loads the plugin.
Docker and local Grafana
When the server runs in Docker and Grafana runs on the host, use http://host.docker.internal:3000 as the Grafana URL instead of http://localhost:3000.
Binary instead of Docker
The server also ships as a binary, mcp-grafana. To use it, point the server entry in your agent's MCP config at mcp-grafana instead of docker, with the same two settings. The mcp-grafana README has examples for each agent.
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.
- 9d ago Changed · -106 lines · +14 tokens per session 1cb0cfaf5594
- 2mo ago First seen · 194 lines · 73 tokens per session scan A a2e25518e57f
grafana-mcp-tools is a skill published in the GitHub repository grafana/ai-marketplace (19 stars, last pushed 3d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,233 once invoked, about $0.0003 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 2026-08-30.
grafana-mcp-tools compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grafana-mcp-toolsgrafana/ai-marketplace | Skill | 19 | 3d ago | Apache-2.0 | A | 87 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |