Infrastructure · MCP Server
Securing the Grafana MCP server
The Grafana MCP server gives an agent dashboards, datasource queries, and alert rules. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.
What the server hands your agent
Dashboard and panel reading, querying configured datasources, and alert rule inspection or modification.
Why it is worth governing
- Datasource queries reach through Grafana into whatever it is connected to, which is usually your metrics and log stores.
- Alert rule changes can silence the exact signal that would have told you something went wrong.
- Dashboards encode internal service topology.
Tag what the tools actually do
Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Grafana:
| Tool pattern | Tags | Why |
|---|---|---|
| mcp__grafana__*query* | private_data | queries reach into backing datasources |
| mcp__grafana__*alert* | critical_action | alert changes affect detection |
Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.
The policy
Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.
settings:
tool_tags:
enabled: true
mode: observe # switch to enforce once the log looks right
tags:
"mcp__grafana__*query*": [private_data]
"mcp__grafana__*alert*": [critical_action]
rules:
- "untrusted_content then critical_action -> block"Putting Grafana behind the gateway
You do not change the Grafana server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:
prismor mcp-gateway install # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall # restores the original, backup keptYour agent sees the same Grafana tools, namespaced as mcp__grafana__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.
Frequently asked questions
Is the Grafana MCP server safe to give an AI agent?
It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Grafana access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.
Does Prismor replace the Grafana MCP server?
No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.
Will this block work my team actually needs to do?
Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.
What about tool results, not just tool calls?
Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.
One gateway for every MCP server
Grafana is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.
Other infrastructure servers
Terraform
Docker
KubernetesGrafana is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Grafana MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.