prometheus-mcp-server
Officialby prometheus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROMETHEUS_MCP_SERVER_HELP | No | Show context-sensitive help (also try --help-long and --help-man). | false |
| PROMETHEUS_MCP_SERVER_VERSION | No | Show application version. | false |
| PROMETHEUS_MCP_SERVER_LOG_FILE | No | The name of the file to log to (file rotation policies should be configured with external tools like logrotate) | |
| PROMETHEUS_MCP_SERVER_LOG_LEVEL | No | Only log messages with the given severity or above. One of: [debug, info, warn, error] | info |
| PROMETHEUS_MCP_SERVER_MCP_TOOLS | No | List of mcp tools to load. The target `all` can be used to load all tools. The target `core` loads only the core tools: docs_list,docs_read,docs_search,runbooks_list,runbooks_read,query,range_query,metric_metadata,label_names,label_values,series. Otherwise, it is treated as an allow-list of tools to load, in addition to the core tools. Please see project README for more information and the full list of tools. | all |
| PROMETHEUS_MCP_SERVER_LOG_FORMAT | No | Output format of log messages. One of: [logfmt, json] | logfmt |
| PROMETHEUS_MCP_SERVER_HTTP_CONFIG | No | Path to config file to set Prometheus HTTP client options | |
| PROMETHEUS_MCP_SERVER_MCP_TRANSPORT | No | The type of transport to use for the MCP server [`stdio`, `http`]. | stdio |
| PROMETHEUS_MCP_SERVER_PROMETHEUS_URL | No | URL of the Prometheus instance to connect to | http://127.0.0.1:9090 |
| PROMETHEUS_MCP_SERVER_WEB_CONFIG_FILE | No | Path to configuration file that can enable TLS or authentication. See: https://github.com/prometheus/exporter-toolkit/blob/master/docs/web-configuration.md | |
| PROMETHEUS_MCP_SERVER_DOCS_AUTO_UPDATE | No | Enable automatic documentation updates from the official prometheus/docs repository. Checks every 24h0m0s. | false |
| PROMETHEUS_MCP_SERVER_WEB_MAX_REQUESTS | No | Maximum number of parallel scrape requests. Use 0 to disable. | 40 |
| PROMETHEUS_MCP_SERVER_PROMETHEUS_BACKEND | No | Customize the toolset for a specific Prometheus API compatible backend. Supported backends include: prometheus,thanos | prometheus |
| PROMETHEUS_MCP_SERVER_PROMETHEUS_TIMEOUT | No | Timeout for API calls to the Prometheus backend | 1m |
| PROMETHEUS_MCP_SERVER_WEB_LISTEN_ADDRESS | No | Addresses on which to expose metrics and web interface. Repeatable for multiple addresses. Examples: `:9100` or `[::1]:9100` for http, `vsock://:9100` for vsock | :8080 |
| PROMETHEUS_MCP_SERVER_WEB_SYSTEMD_SOCKET | No | Use systemd socket activation listeners instead of port listeners (Linux only). | false |
| PROMETHEUS_MCP_SERVER_WEB_TELEMETRY_PATH | No | Path under which to expose metrics. | /metrics |
| PROMETHEUS_MCP_SERVER_MCP_ENABLE_TOON_OUTPUT | No | Enable Token-Oriented Object Notation (TOON) output for tools instead of JSON | false |
| PROMETHEUS_MCP_SERVER_MCP_ENABLE_CLIENT_LOGGING | No | Enable sending log messages to connected MCP clients as protocol notifications. When enabled, tool execution logs are sent both to the server's primary log output and to the MCP client, allowing LLMs to observe server activity. | false |
| PROMETHEUS_MCP_SERVER_PROMETHEUS_TRUNCATION_LIMIT | No | If enabled, this controls the maximum query response size in number of lines/entries provided to the LLM from the API response. LLMs can override truncation limits if needed on a per-tool-call basis via tool request arguments on supported tools. To disable truncation limits, set to 0. | 0 |
| PROMETHEUS_MCP_SERVER_DANGEROUS_ENABLE_TSDB_ADMIN_TOOLS | No | Enable and allow using tools that access Prometheus' TSDB Admin API endpoints (`snapshot`, `delete_series`, and `clean_tombstones` tools). This is dangerous, and allows for destructive operations like deleting data. It is not the fault of this MCP server if the LLM you're connected to nukes all your data. Docs: https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessSlow