VictoriaMetrics-mcp-server
This MCP server provides an interface for AI assistants to interact with VictoriaMetrics time series database for monitoring and observability data:
Write custom metrics - Insert time series data with metric tags, values, and timestamps
Import Prometheus format data - Ingest metrics in Prometheus exposition format for ecosystem compatibility
Query current values - Execute PromQL queries to retrieve instantaneous metric values at specific points in time
Query time ranges - Run PromQL queries over specified time periods with configurable start, end, and resolution steps for historical analysis
Discover labels - Retrieve all unique label names to explore metric structure
Get label values - Fetch all unique values for specific labels to understand metric dimensions
Integrate with Claude Desktop - Install via Smithery or manual NPX configuration
This server bridges AI assistants and VictoriaMetrics, enabling automated metric analysis, data ingestion, and time-series exploration through natural language interactions.
Enables importing Prometheus exposition format data and executing PromQL queries against the VictoriaMetrics database.
Provides tools for reading and writing time series data to VictoriaMetrics, including capabilities for querying data over specific time ranges, importing Prometheus format data, and retrieving label information.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@VictoriaMetrics-mcp-server query range for http_requests_total over the last hour"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
VictoriaMetrics MCP Server
MCP Server for the VictoriaMetrics.
Installing via Smithery
To install VictoriaMetrics Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @yincongcyincong/victoriametrics-mcp-server --client claudeDebug
npx @modelcontextprotocol/inspector -e VM_URL=http://127.0.0.1:8428 node src/index.js
NPX
{
"mcpServers": {
"victoriametrics": {
"command": "npx",
"args": [
"-y",
"@yincongcyincong/victoriametrics-mcp-server"
],
"env": {
"VM_URL": "",
"VM_SELECT_URL": "",
"VM_INSERT_URL": ""
}
}
}
}📊 VictoriaMetrics Tools API Documentation
Related MCP server: ClickHouse MCP Server
1. vm_data_write
Description: Write data to the VictoriaMetrics database.
Input Parameters:
Parameter | Type | Description | Required |
|
| Tags of the metric | ✅ |
|
| Array of metric values | ✅ |
|
| Array of timestamps in Unix seconds | ✅ |
2. vm_prometheus_write
Description: Import Prometheus exposition format data into VictoriaMetrics.
Input Parameters:
Parameter | Type | Description | Required |
|
| Metrics in Prometheus exposition format | ✅ |
3. vm_query_range
Description: Query time series data over a specific time range.
Input Parameters:
Parameter | Type | Description | Required |
|
| PromQL expression | ✅ |
|
| Start timestamp in Unix seconds | ⛔️ |
|
| End timestamp in Unix seconds | ⛔️ |
|
| Query resolution step width (e.g., | ⛔️ |
Only
queryis required; the other fields are optional.
4. vm_query
Description: Query the current value of a time series.
Input Parameters:
Parameter | Type | Description | Required |
|
| PromQL expression to evaluate | ✅ |
|
| Evaluation timestamp in Unix seconds | ⛔️ |
5. vm_labels
Description: Get all unique label names.
Input Parameters: None
6. vm_label_values
Description: Get all unique values for a specific label.
Input Parameters:
Parameter | Type | Description | Required |
|
| Label name to get values for | ✅ |
Available Tools
6 toolsvm_data_writeC
Write data to the VM database
Inputs: metric (required), values (required), timestamps (required).
vm_labelsB
Get all unique label names
Inputs: no named parameters.
vm_label_valuesC
Get all unique values for a specific label
Inputs: label (required).
vm_prometheus_writeC
mport Prometheus exposition format data into VictoriaMetrics
Inputs: data (required).
vm_queryC
Query current value of a time series
Inputs: query (required), time.
vm_query_rangeC
Query time series over a time range
Inputs: query (required), start, end, step.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: writing data, retrieving metadata about labels, querying current values, and querying over time ranges. The descriptions make it easy to differentiate between tools like vm_query (current value) and vm_query_range (time range).
All tools follow a consistent 'vm_' prefix with snake_case naming, using descriptive verb_noun patterns (e.g., vm_data_write, vm_query_range). There are no deviations in style or convention across the set.
With 6 tools, this is well-scoped for a VictoriaMetrics server, covering core operations like data ingestion, label exploration, and querying without being overwhelming. Each tool earns its place in the workflow.
The toolset covers essential CRUD-like operations for time series data: writing (vm_data_write, vm_prometheus_write), reading (vm_query, vm_query_range), and metadata exploration (vm_labels, vm_label_values). A minor gap might be the lack of explicit deletion or update tools, but agents can work around this given the domain's typical usage patterns.
Maintenance
Related MCP Connectors
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for interacting with Prometheus metrics and data.17MIT
- Apache 2.0
- AlicenseNot gradedqualityBmaintenanceThe implementation of Model Context Protocol (MCP) server for VictoriaMetrics247Apache 2.0
- AlicenseNot gradedqualityBmaintenanceThe implementation of Model Context Protocol (MCP) server for VictoriaLogs.112Apache 2.0