Skip to content
Agent Search Engine.
Submit a tool
Menu

Record · grafana-mcpMCP serverCosts not checkedRecord checked Sep 23, 2026

Grafana MCP Server

Grafana's official MCP server for dashboards, datasources, Prometheus and Loki queries and more.

Visit Grafana MCP Server →View repository

Sources and review

Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.

Best for

On-call engineers who want an assistant to pull metrics and logs while investigating incidents.

Avoid if

You run a Grafana version older than 9.0; some datasource features rely on newer APIs.

About Grafana MCP Server

Grafana Labs' MCP server gives AI assistants access to a Grafana instance and its ecosystem: search dashboards, run panel queries, and query datasources including Prometheus, Loki, InfluxDB and SQL sources. It works with self-hosted Grafana and Grafana Cloud, authenticating with a service account token, and can run through uv, Docker, a binary or Helm.

Grafana MCP Server is listed in this index written primarily in Go, with 3.6k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.

Before connecting: access and data

This record's specific permissions have not been reviewed by ASE. Read the publisher's documentation before copying setup or connecting.

  • List the accounts, files and services the enabled tools can read, change or execute. Check your actual credentials and discovered tools.
  • Use narrowly scoped credentials and read-only mode where supported. Review proposed writes before approving them; a generated configuration does not apply these limits for you.
  • Local launch is not local-only data processing. External services receive requests, and your client may pass tool results to its model provider. Check both destinations before sharing private data.
  • Keep keys and browser session files out of shared config, repositories and screenshots. Know how to disconnect the server and separately revoke its credentials or account sessions.

Read the setup guide →

Add Grafana MCP Server to your MCP client

Generated from the launch command in the project's README. Your client starts the server on demand. Replace <your-token> with your own value first.

Claude CodeRun in your terminal
claude mcp add grafana-mcp -e GRAFANA_URL=http://localhost:3000 -e 'GRAFANA_SERVICE_ACCOUNT_TOKEN=<your-token>' -- uvx mcp-grafana
Cursor~/.cursor/mcp.json or .cursor/mcp.json
{
  "mcpServers": {
    "grafana-mcp": {
      "command": "uvx",
      "args": ["mcp-grafana"],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<your-token>"
      }
    }
  }
}
VS Code.vscode/mcp.json
{
  "servers": {
    "grafana-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-grafana"],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<your-token>"
      }
    }
  }
}
Claude Desktopclaude_desktop_config.json
{
  "mcpServers": {
    "grafana-mcp": {
      "command": "uvx",
      "args": ["mcp-grafana"],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<your-token>"
      }
    }
  }
}
Codex~/.codex/config.toml
[mcp_servers.grafana-mcp]
command = "uvx"
args = ["mcp-grafana"]
env = { GRAFANA_URL = "http://localhost:3000", GRAFANA_SERVICE_ACCOUNT_TOKEN = "<your-token>" }

Check the project's README for required accounts, keys and permissions before connecting. Setup guide for each client →

For agent buildersMake your product part of the discovery.Explore advertising