---
title: "Set up the Grafana MCP server | Grafana Cloud documentation"
description: "Install and run the Grafana MCP server using uvx, Docker, a binary, or Helm."
---

> For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt).

# Set up the Grafana MCP server

Choose how you install and run the open source Grafana MCP server. Start with `uvx` for the least setup, or use Docker, a downloaded binary, or Helm when that fits your environment. Refer to [Clients](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/clients) for client-specific steps and [Client configuration examples](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/client-configuration-examples) for copy-paste MCP JSON (debug, TLS, and more).

> Note
> 
> These instructions cover the open source server, which you install and run yourself. If you want to connect an external AI agent to Grafana Cloud without running your own server, refer to [Grafana Cloud MCP server](/docs/grafana-cloud/ai-tools/mcp-servers/cloud-mcp/) instead.

- [Install with uvx](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/install-with-uvx/)  
  Run the Grafana MCP server with uvx for a zero-install setup.
- [Install with Docker](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/install-with-docker/)  
  Run the Grafana MCP server using the official Docker image.
- [Install the binary](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/install-the-binary/)  
  Download or build the Grafana MCP server binary.
- [Deploy with Helm](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/deploy-with-helm/)  
  Deploy the Grafana MCP server to Kubernetes using the Helm chart.
- [Client configuration examples](/docs/grafana-cloud/ai-tools/mcp-servers/oss-mcp/set-up/client-configuration-examples/)  
  Example MCP client JSON for uvx, binary, Docker, VS Code, and debug mode.