prometheus-mcp-server
@yshngg
About prometheus-mcp-server
A Prometheus Model Context Protocol Server.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"prometheus-mcp-server-yshngg": {
"command": "docker",
"args": [
"pull",
"ghcr.io/yshngg/prometheus-mcp-server:latest"
]
}
}
}Tools
4Return currently loaded configuration file
Return flag values that Prometheus was configured with
Trigger a reload of the Prometheus configuration and rule files
Trigger a graceful shutdown of Prometheus
Overview
What is prometheus-mcp-server?
A Golang-based Model Context Protocol (MCP) server that enables natural language interactions with Prometheus metrics and queries. It acts as a bridge between MCP-compatible clients (like Claude Desktop) and Prometheus servers, providing full compatibility with the Prometheus HTTP API v1.
How to use prometheus-mcp-server?
Run the server by specifying the Prometheus address and transport. Use Docker, a pre-built binary, or build from source. Example: prometheus-mcp-server --prom-addr="http://localhost:9090" (defaults to stdio transport). Configurable flags: -prom-addr, -transport (stdio, http, sse), -mcp-addr.
Key features of prometheus-mcp-server
- Complete Prometheus API v1 coverage via MCP tools
- Instant and range query execution
- Metadata discovery (series, labels, values)
- Target, rule, and alert management
- TSDB administration (snapshots, series deletion)
- Multiple transport options (HTTP, SSE, stdio)
Use cases of prometheus-mcp-server
- Query Prometheus metrics using natural language from an MCP client
- Monitor alerting rules and targets without writing PromQL directly
- Retrieve historical metric data over defined time ranges
- Perform administrative tasks like TSDB snapshots or series deletion
- Integrate Prometheus observability into AI-powered assistants
FAQ from prometheus-mcp-server
—
What dependencies are required?
Go 1.23+ and a running Prometheus server v2.x, plus a compatible MCP client.
How is data accessed?
All queries go directly against the Prometheus HTTP API; no data is stored locally by the server.
What transport protocols are supported?
stdio (default), HTTP, and SSE (deprecated). HTTP is recommended for web integrations.
Are there any known limitations?
—
How is authentication handled?
—
Frequently asked questions
What dependencies are required?
Go 1.23+ and a running Prometheus server v2.x, plus a compatible MCP client.
How is data accessed?
All queries go directly against the Prometheus HTTP API; no data is stored locally by the server.
What transport protocols are supported?
stdio (default), HTTP, and SSE (deprecated). HTTP is recommended for web integrations.
Basic information
More Developer Tools MCP servers
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Serena
oraiosA powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
Deepwiki MCP Server
regenrek📖 MCP server for fetch deepwiki.com and get latest knowledge in Cursor and other Code Editors
Vibgrate MCP
VibgrateQuery your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
extentos
Asger mølgaardExtentos is a multi-vendor development platform for adding smart-glasses capabilities to existing iOS and Android apps. The simplest analogy is Stripe for smart glasses:
Comments