Official agent skill

Assistant MCP

by grafana in grafana/skills

Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the mcp-grafana Model Context Protocol server.

OfficialApache-2.0Auto-check passedDevOps & Cloud

Install Assistant MCP

skills CLI
$ npx skills add grafana/skills --skill assistant-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install grafana/skills assistant-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/grafana/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/grafana-cloud/assistant-mcp .claude/skills/assistant-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
assistant-mcp
GitHub stars
282
Token cost
~1.2k tokens
SKILL.md length
376 words
Files
4 (incl. references)
Skills in repo
51
Repo updated
First seen
Licence
Apache-2.0

At a glance

Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the mcp-grafana Model Context Protocol server.

  • Works in 3 steps: Get a service-account token: Grafana… → Wire ~/.claude/settings.json (or… → Restart Claude Code, then verify
  • Connecting Claude Code to Grafana
  • SKILL.md covers Common Workflows, Security considerations, References and External resources
  • Calls go; needs GRAFANA_API_KEY

What it does

Assistant MCP is an agent skill from grafana/skills, published by the product's own GitHub organization. Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the mcp-grafana Model Context Protocol server. Installs the server with go install, generates a Grafana service-account token, wires ~/.claude/settings.json or ~/.cursor/mcp.json with the command + env block, runs --disable-write for safer read-only sessions, switches to SSE transport for team-shared / VS Code setups, and verifies with /mcp + a listdatasources round-trip. Use when connecting Claude Code to Grafana, setting…

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/a2a.md`, `references/sse-transport.md` and `references/tools.md`).

It sits in DevOps & Cloud, covering Monitoring and alerting and MCP servers. It works with Model Context Protocol, Grafana and Visual Studio Code. The licence is Apache-2.0.

When your agent uses it

  • Connecting Claude Code to Grafana
  • Setting up MCP for Grafana
  • Configuring the Grafana MCP server
  • Using Grafana tools in Cursor/VS Code

Example prompts

  • “give my agent Grafana access”
  • “let Claude see my metrics”
  • “Cursor + Grafana”
  • “/assistant-mcp”

Requirements

  • A credential in GRAFANA_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Get a service-account token: Grafana Cloud → Administration → Service Accounts → create with Viewer role (add Editor only if you need…
  2. Wire ~/.claude/settings.json (or project-local .claude/settings.json)
  3. Restart Claude Code, then verify

What it can do on your machine

Read from SKILL.md and the folder at commit 1ccacf2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • grafana.com
    • github.com
    • spec.modelcontextprotocol.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GRAFANA_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Assistant MCP loads about 1.2k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 212 tokens; SKILL.md has 376 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~212
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from grafana/skills at commit 1ccacf2, republished under its Apache-2.0 licence (© grafana). 376 words, ~1,238 tokens.

Download SKILL.mdSave it as .claude/skills/assistant-mcp/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
assistant-mcp
description
Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the `mcp-grafana` Model Context Protocol server. Installs the server with `go install`, generates a Grafana service-account token, wires `~/.claude/settings.json` or `~/.cursor/mcp.json` with the `command` + `env` block, runs `--disable-write` for safer read-only sessions, switches to SSE transport for team-shared / VS Code setups, and verifies with `/mcp` + a `list_datasources` round-trip. Use when connecting Claude Code to Grafana, setting up MCP for Grafana, configuring the Grafana MCP server, using Grafana tools in Cursor/VS Code, querying Grafana from an AI agent, sharing the MCP server across a team — even when the user says "give my agent Grafana access", "let Claude see my metrics", or "Cursor + Grafana" without saying "MCP".
license
Apache-2.0

Grafana Cloud MCP Server Setup

The Grafana MCP server exposes Grafana Cloud capabilities as tools that AI agents can call via the Model Context Protocol. Agents can then query metrics, search dashboards, manage alerts, investigate incidents, and interact with Fleet Management without leaving the coding environment.

Transports: stdio (agent spawns the server as a subprocess, simplest), or SSE (server runs independently, agents connect via HTTP — see references/sse-transport.md).

Common Workflows

Connecting Claude Code to Grafana (stdio)
bash
# 1. Install the server
go install github.com/grafana/mcp-grafana/cmd/mcp-grafana@latest

# 2. Verify the binary
mcp-grafana --version
# If "command not found": ensure $GOPATH/bin (or $HOME/go/bin) is on PATH.
  1. Get a service-account token: Grafana Cloud → Administration → Service Accounts → create with Viewer role (add Editor only if you need writes) → generate token. Note the Grafana URL (e.g. https://myorg.grafana.net).

  2. Wire ~/.claude/settings.json (or project-local .claude/settings.json):

    json
    {
      "mcpServers": {
        "grafana": {
          "command": "mcp-grafana",
          "args": ["--disable-write"],
          "env": {
            "GRAFANA_URL": "https://myorg.grafana.net",
            "GRAFANA_API_KEY": "glsa_xxxx"
          }
        }
      }
    }

    --disable-write is the safer default — drop it once you've verified the read path works.

  3. Restart Claude Code, then verify:

    /mcp

    The grafana server should appear with its tool list. Then ask:

    What data sources are configured in my Grafana instance?

    A clean response = working. If the tool call fails:

    • Check GRAFANA_URL has no trailing slash
    • Confirm the API key hasn't expired
    • Re-run with mcp-grafana --debug to see raw request/response
Connecting Cursor

Same Grafana token. Settings → Features → MCP Servers (or edit ~/.cursor/mcp.json):

json
{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": ["--disable-write"],
      "env": {
        "GRAFANA_URL": "https://myorg.grafana.net",
        "GRAFANA_API_KEY": "glsa_xxxx"
      }
    }
  }
}

Verify the same way — Cursor surfaces MCP servers in its agent panel; run a query like "list dashboards tagged kubernetes".

Show full SKILL.md (174 more words)Show less
Sharing the server across a team (SSE)

Switch from stdio to SSE so the server runs once and many agents connect to it. Full setup with VS Code config in references/sse-transport.md.

Security considerations

  • API keys belong in env vars or a secrets manager — never in committed files.
  • Use --disable-write for shared environments and CI; only lift it on the specific machine where the agent should be allowed to mutate Grafana.
  • Scope service-account permissions to the minimum: Viewer is enough for queries and dashboard reads. Only grant Editor when the agent needs to create dashboards or annotations.
  • Rotate tokens periodically via Administration → Service Accounts.

References

  • references/tools.md — full list of MCP tools exposed (query / dashboard / alerting / Fleet Management / annotations) and how to discover the live set
  • references/sse-transport.md — SSE setup for team sharing and VS Code, with stdio-vs-SSE decision matrix + common failure modes
  • references/a2a.md — Agent-to-Agent (A2A) protocol for delegating reasoning to the Grafana Assistant (vs direct tool calls via MCP)

External resources

© grafana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/grafana-cloud/assistant-mcp of grafana/skills.

  • SKILL.md
  • references/a2a.md
  • references/sse-transport.md
  • references/tools.md

Open the folder on GitHubat commit 1ccacf2

Compare with similar skills

Assistant MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Assistant MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Assistant MCP this skillgrafana/skills282—~1.2kAutomated safety check: PassApache-2.0
Devsydevsy-org/devsy112—~1.7kAutomated safety check: PassMPL-2.0
Syncmetapawurb/hotpath-rs1.9k—~1.2kAutomated safety check: NotesMIT
Greptimedb Perses DashboardGreptimeTeam/dashboard111—~3.9kAutomated safety check: PassApache-2.0
AWS Cost Operationszxkane/aws-skills367—~2.4kAutomated safety check: PassMIT
Archestra Dev Observabilityarchestra-ai/archestra4.4k—~1.2kAutomated safety check: PassCustom licence

Similar skills

  • Devsy

    devsy-org/devsy

    Operate Devsy workspaces and providers for end users. An agent skill from devsy-org/devsy.

    112 GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Syncmeta

    pawurb/hotpath-rs

    Sync changes from the hotpath, hotpath-macros and hotpath-drain crates to their meta counterparts (hotpath-meta, hotpath-macros-meta and hotpath-drain-meta).

    1.9k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Greptimedb Perses Dashboard

    GreptimeTeam/dashboard

    Generate Perses dashboards or single panels for GreptimeDB. An agent skill from GreptimeTeam/dashboard.

    111 GitHub stars~3.9k tokensUpdated today
    DevOps & CloudAuto-check passed
  • AWS Cost Operations

    zxkane/aws-skills

    AWS cost optimization, monitoring, and operational excellence expert.

    367 GitHub stars~2.4k tokensUpdated 3 mo ago
    DevOps & CloudAuto-check passed
  • Archestra Dev Observability

    archestra-ai/archestra

    A skill your agent uses when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup.

    4.4k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Frontmcp Observability

    agentfront/frontmcp

    A skill your agent uses when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server.

    146 GitHub stars~4.6k tokensUpdated today
    DevOps & CloudAuto-check passed

More from grafana/skills

All 51 skills in this repo
  • K6 Docs

    grafana/skills

    Official

    Write or review k6 documentation across the three k6 repositories - k6-DefinitelyTyped (TypeScript types), k6-docs (user documentation), and k6 (release notes / changelog).

    282 GitHub stars~678 tokensUpdated yesterday
    Auto-check passed
  • Alerting Irm

    grafana/skills

    Official

    Configure Grafana Alerting, Incident Response Management (IRM), and SLOs end-to-end — provisions Grafana-managed and data-source-managed alert rules, contact points (Slack/PagerDuty/email/webhook)…

    282 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Dashboarding

    grafana/skills

    Official

    Build, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table / heatmap / logs / traces / node-graph), gridPos 24-column layout, units…

    282 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • K6 Perf Test Website

    grafana/skills

    Official

    A skill your agent uses when the user wants to performance-test, load-test, or stress-test a public website end-to-end with k6.

    282 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Promql

    grafana/skills

    Official

    Write, validate, and optimize PromQL for Prometheus / Grafana Mimir / Grafana Cloud Metrics.

    282 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed
  • Adaptive Metrics

    grafana/skills

    Official

    Cut Grafana Cloud Metrics cost by shrinking active-series count with Adaptive Metrics aggregation rules — auto-recommendations from query history, custom exact/regex rules, label-drop config…

    282 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Questions about Assistant MCP

What does Assistant MCP do?

Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the mcp-grafana Model Context Protocol server. Assistant MCP is an agent skill from grafana/skills, published by the product's own GitHub organization. Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the mcp-grafana Model Context Protocol server.

When should I use Assistant MCP?

Assistant MCP fits situations like: connecting Claude Code to Grafana; setting up MCP for Grafana; configuring the Grafana MCP server; using Grafana tools in Cursor/VS Code.

How do I install Assistant MCP in Claude Code?

Run `npx skills add grafana/skills --skill assistant-mcp -a claude-code`. Or copy the skill folder (skills/grafana-cloud/assistant-mcp in grafana/skills) into .claude/skills/assistant-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Assistant MCP in Codex?

Run `npx skills add grafana/skills --skill assistant-mcp -a codex`. Or copy the skill folder (skills/grafana-cloud/assistant-mcp in grafana/skills) into .agents/skills/assistant-mcp in your project. Codex loads it when a task matches its description.

Can I use Assistant MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add grafana/skills --skill assistant-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assistant-mcp, .gemini/skills/assistant-mcp, .github/skills/assistant-mcp and .opencode/skills/assistant-mcp in your project.

What does Assistant MCP need to run?

Going by SKILL.md and its folder, Assistant MCP needs the command-line tools its instructions call (go) and credentials named GRAFANA_API_KEY. Our summary lists: A credential in GRAFANA_API_KEY.

Does Assistant MCP access the network?

SKILL.md names 3 domains. As links in the text: grafana.com, github.com and spec.modelcontextprotocol.io. This is read from the text; nothing was executed.

Is Assistant MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Assistant MCP use?

Assistant MCP is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Assistant MCP use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.

What are the alternatives to Assistant MCP?

Skills that share tags, products or a category with Assistant MCP: Devsy (devsy-org/devsy, 112 stars), Syncmeta (pawurb/hotpath-rs, 1.9k stars), Greptimedb Perses Dashboard (GreptimeTeam/dashboard, 111 stars) and AWS Cost Operations (zxkane/aws-skills, 367 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assistant MCP?

grafana (a GitHub organization, an official publisher) maintains it in grafana/skills, which has 282 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on October 8, 2026.

Source: grafana/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.