An [MCP (Model Context Protocol)][mcp] server for Prometheus and Mimir, written in Go. Deployed in-cluster at Giant Swarm to give AI assistants
Mcp prometheus mcp server connects MCP Prometheus to AI assistants that speak the Model Context Protocol. An [MCP (Model Context Protocol)][mcp] server for Prometheus and Mimir, written in Go. Deployed in-cluster at Giant Swarm to give AI assistants authenticated, multi-tenant access to metrics infrastructure.
An [MCP (Model Context Protocol)][mcp] server for Prometheus and Mimir, written in Go. Deployed in-cluster at Giant Swarm to give AI assistants authenticated, multi-tenant access to metrics infrastructure.
Once connected, the assistant can call these 4 tools directly:
Tenancy — The Tenancy tool exposed by this serverObservability — The Observability tool exposed by this serverEndpoints — The Endpoints tool exposed by this serverAdvanced — Large query results are automatically truncated with guidance for the AI to refine its querySetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 8 environment variables: PROMETHEUS_URL, PROMETHEUS_TOKEN, MCP_OAUTH_ENCRYPTION_KEY, VALKEY_URL, DEX_ISSUER_URL, DEX_CLIENT_ID, DEX_CLIENT_SECRET, DEX_REDIRECT_URL. Keep credentials in your client's env block or a secrets manager rather than committing them.
Monitoring servers replace the paste-the-stack-trace ritual with an assistant that reads the real event, with all its surrounding context intact. MCP Prometheus sits in that group, and the shape of its toolset — Tenancy, Observability, Endpoints among others — tells you what it is really for. Worth comparing against the other monitoring security servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Tenancy | The Tenancy tool exposed by this server. |
| Observability | The Observability tool exposed by this server. |
| Endpoints | The Endpoints tool exposed by this server. |
| Advanced | Large query results are automatically truncated with guidance for the AI to refine its query. |
| Variable | Description | Required |
|---|---|---|
| PROMETHEUS_URL | Endpoint or connection string the server talks to. | Yes |
| PROMETHEUS_TOKEN | Credential the server authenticates with. | Yes |
| MCP_OAUTH_ENCRYPTION_KEY | Credential the server authenticates with. | Yes |
| VALKEY_URL | Credential the server authenticates with. | Yes |
| DEX_ISSUER_URL | Endpoint or connection string the server talks to. | Yes |
| DEX_CLIENT_ID | Configuration value read at startup. | Optional |
| DEX_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| DEX_REDIRECT_URL | Endpoint or connection string the server talks to. | Yes |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.