# Grafana MCP Server

> Grafana MCP Server is an officially published MCP server from Grafana Labs. Anomity scores its risk at 35 out of 100 (medium). It matches 1 dangerous capability combination.

- **Canonical URL:** https://catalog.anomity.ai/mcp/grafana-mcp-server
- **Kind:** MCP server
- **Publisher:** Grafana Labs
- **Trust level:** official
- **Risk score:** 35/100 (medium)
- **Website:** https://grafana.com/docs/grafana/latest/observability-as-code/mcp-server/
- **Documentation:** https://grafana.com/docs/grafana/latest/observability-as-code/mcp-server/
- **Last updated:** 2026-09-02
- **JSON:** https://catalog.anomity.ai/api/entries/mcp/grafana-mcp-server

## Description

Grafana's official server lets an agent query dashboards, datasources, alert rules, and incidents, so an assistant investigating an outage can pull the actual metrics rather than a screenshot of them.

Declared capabilities are outbound network access, credential access, and database reads through the connected datasources. That last one is the sharp edge: Grafana is a window onto whatever it is wired to, so the effective reach of this server is the union of every datasource in the organisation, which is usually broader than the person connecting it expects. Scope by folder and datasource, and prefer viewer-level credentials for assistants.

## Why it scored 35

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Published by the vendor | -40 | trust offset |  |
| 1 high-risk capability: credentials:access | +10 | high |  |
| Database exfiltration risk (high) | +15 | high | Database read combined with outbound network can exfiltrate production data. |

Clamped result: **35/100**, band **medium**.

## Capabilities

| Capability | Name | Security implication |
| --- | --- | --- |
| `network:outbound` | Outbound network | Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access. |
| `credentials:access` | Credentials access | Reads provider API keys, OAuth tokens, or other secrets from the host keychain or environment. |
| `database:read` | Database read | Reads from connected databases. Useful for query and analytics agents; risky when combined with outbound network. |

## Dangerous combinations matched

### Database exfiltration risk (high)

Database read combined with outbound network can exfiltrate production data.

Capabilities: `database:read`, `network:outbound`

## Related MCP servers

- [Airtable MCP Server](https://catalog.anomity.ai/mcp/airtable-mcp-server) — risk 45 (medium)
- [Cloudflare MCP Server](https://catalog.anomity.ai/mcp/cloudflare-mcp-server) — risk 45 (medium)
- [MongoDB MCP Server](https://catalog.anomity.ai/mcp/mongodb-mcp-server) — risk 45 (medium)
- [Neon MCP Server](https://catalog.anomity.ai/mcp/neon-mcp-server) — risk 45 (medium)
- [PostgreSQL](https://catalog.anomity.ai/mcp/postgres) — risk 45 (medium)
- [Supabase MCP Server](https://catalog.anomity.ai/mcp/supabase-mcp-server) — risk 45 (medium)

---

Source: Anomity Catalog (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json