VictoriaMetrics MCP Server

Fast, cost-effective monitoring solution and time-series database compatible with Prometheus

Tools

Last Updated

Apr 7, 2026

What is the VictoriaMetrics MCP Server?

The VictoriaMetrics MCP server gives AI agents structured, permission-aware access to VictoriaMetrics through the Model Context Protocol. With 24 pre-built actions, agents can read, create, and update VictoriaMetrics data on behalf of authorized users.

Willow ships the VictoriaMetrics MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how VictoriaMetrics is being used by every AI agent in your stack.

Tools

Execute Instant Query

Execute a MetricsQL query at a single point in time. MetricsQL is a PromQL-compatible query language with additional functions and optimizations. Returns the current value of metrics matching the query. Use this for getting the latest state of metrics, checking current values, or evaluating expressions at a specific timestamp.

Execute Range Query

Execute a MetricsQL query over a range of time. Returns time series data over the specified time window with the given resolution step. Use this for plotting graphs, analyzing trends over time, or getting historical metric values. VictoriaMetrics optimizes range queries for better performance than Prometheus. Supports relative time ranges and automatic step adjustment.

Query Top K Series

Find the top K time series by value using VictoriaMetrics' optimized topk functions. Returns only the highest-value series, which is more efficient than fetching all series and sorting. Use this for identifying top consumers, finding anomalies, or focusing on the most important metrics. Supports both instant and range queries with topk operators.

Execute Query with Trace

Execute a MetricsQL query and get detailed execution trace information. Returns query results along with performance metrics and execution steps. Use this for debugging slow queries, understanding query execution, optimizing performance, or troubleshooting unexpected results. VictoriaMetrics provides enhanced tracing compared to Prometheus.

Find Series by Label Matchers

Find time series that match specific label selectors. Returns a list of label sets identifying each matching series. Use this to discover what metrics exist, find series with specific labels, or explore available time series data. VictoriaMetrics supports extended label matching with =, !=, =~, !~ operators and can handle high-cardinality series efficiently.

List All Label Names

Get a list of all label names used across time series. Returns an array of label name strings. Use this to discover what labels are available, understand the labeling scheme, or build dynamic queries. VictoriaMetrics can efficiently handle databases with millions of unique labels. Supports filtering by time range and series matchers.

Get Label Values

Get all values for a specific label name. Returns an array of strings representing all unique values that label has across time series. Use this to discover what instances, jobs, or other label values exist in your metrics. VictoriaMetrics can efficiently return values even for high-cardinality labels. Supports time range filtering.

Get Metric Metadata

Get metadata about metrics including type and help text. Returns information about what each metric measures and its type (counter, gauge, histogram, summary). Use this to understand available metrics and their purposes. Note: VictoriaMetrics may have limited metadata compared to Prometheus if metrics are imported without metadata.

Get TSDB Statistics

Get cardinality statistics about the time series database. Returns information about the number of series, label names, label value pairs, and which labels have the highest cardinality. Use this to understand TSDB resource usage, identify high-cardinality labels causing performance or storage issues, plan capacity, or troubleshoot. VictoriaMetrics provides additional statistics compared to Prometheus.

List Metric Names

Get a list of all metric names (time series names) available in VictoriaMetrics. Returns an array of __name__ label values, which are the metric names. Use this for discovering what metrics are being stored, building metric browsers, or validating metric ingestion. Can be filtered by time range and label matchers. This is a convenience wrapper around finding series and extracting __name__ labels.

1 2 3

1–10 of 24 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your VictoriaMetrics MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-victoria-metrics": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/victoria-metrics"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-victoria-metrics": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/victoria-metrics"
    }
  }
}

Claude Code

CLI

claude mcp add willow-victoria-metrics --transport http https://<org>.mcp-s.com/mcp/mcp/victoria-metrics

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/victoria-metrics",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for VictoriaMetrics

Willow adds the layer VictoriaMetrics and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

VictoriaMetrics MCP Server FAQ

What is the VictoriaMetrics MCP server?

The VictoriaMetrics MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write VictoriaMetrics data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's VictoriaMetrics MCP server different from the official one?

The official VictoriaMetrics MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the VictoriaMetrics MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the VictoriaMetrics MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in VictoriaMetrics, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which VictoriaMetrics actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow VictoriaMetrics MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved VictoriaMetrics MCP locally, you'll see it.

What does the VictoriaMetrics MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the VictoriaMetrics MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.