Skip to content
Agentmart
Submit a tool

MCP Vmanomaly

MCP Server for vmanomaly - VictoriaMetrics anomaly detection

Connector by VictoriaMetrics · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 11
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/victoriametrics-mcp-vmanomaly

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP Server for vmanomaly - VictoriaMetrics anomaly detection

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
17 read · 2 write · 0 delete · 2 not yet classified
Secrets
2 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Docker image

Tools by what they do 21

Read from the source code; the running server may list different tools.

Read 17 · Look things up without changing anything.

  • list_models
  • vmanomaly_check_compatibility
  • vmanomaly_estimate_deployment_resources
  • vmanomaly_estimate_inference_capacity
  • vmanomaly_get_autotune_task
  • vmanomaly_get_buildinfo
  • vmanomaly_get_deployment_sizing_profiles
  • vmanomaly_get_metrics
  • vmanomaly_get_model_schema
  • vmanomaly_get_server_models
  • vmanomaly_get_server_queries
  • vmanomaly_health_check
Show 5 more tools
  • vmanomaly_list_models
  • vmanomaly_read_doc_section
  • vmanomaly_search_docs
  • vmanomaly_validate_config
  • vmanomaly_validate_model_config

Write 2 · Create, change, send or run things.

  • vmanomaly_cancel_autotune_task
  • vmanomaly_create_autotune_task

Not yet classified 2 · We could not tell from the name and description.

  • vmanomaly_generate_alert_rule
  • vmanomaly_timeseries_characteristics

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • VMANOMALY_BEARER_TOKEN
  • VMANOMALY_BEARER_TOKEN_FILE

Other settings (environment variables or headers).

  • MCP_DISABLED_TOOLS
  • MCP_DISABLE_RESOURCES
  • MCP_ENABLED_TOOLS
  • MCP_HEARTBEAT_INTERVAL
  • MCP_LISTEN_ADDR
  • MCP_LOG_FILE
  • MCP_LOG_LEVEL
  • MCP_SERVER_MODE
  • VMANOMALY_ENDPOINT
  • VMANOMALY_HEADERS

Network hosts it talks to 1

  • github.com · found in code

Files it touches

  • /dev/stderr
  • /tmp/test.log

Tools (21)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • list_models
  • vmanomaly_cancel_autotune_task

    Request cooperative cancellation of a running shared autotune task.

  • vmanomaly_check_compatibility

    Check if persisted vmanomaly state is compatible with the current or target runtime version. Returns compatibility status and required migration actions.

  • vmanomaly_create_autotune_task

    Start shared unsupervised autotune on sampled query results for one requested model class. Returns a task_id immediately. Use this after choosing a model class from vmanomaly_timeseries_characteristics, then poll vmanomaly_get_autotune_task until done. Pass the same step used for profiling and the final detect-anomalies task/config. Tell the user the budget and anomaly assumption before calling; MCP defaults to optimization_timeout=8, optimization_n_trials=32, and anomaly_percentage=0.02 unless overridden.

  • vmanomaly_estimate_deployment_resources

    Description is built at runtime.

  • vmanomaly_estimate_inference_capacity

    Description is built at runtime.

  • vmanomaly_generate_alert_rule

    Generate a VMAlert rule YAML configuration for anomaly score alerting. Creates a production-ready vmalert rule that triggers when anomaly_score exceeds the threshold. Use this to set up alerting for anomalies detected by vmanomaly.

  • vmanomaly_get_autotune_task

    Get a shared autotune task. While status is running, wait briefly before polling again and never issue concurrent duplicate polls. When status is done, use result_data.data.modelConfig and related result_data fields. Treat error and canceled as terminal.

  • vmanomaly_get_buildinfo

    Get vmanomaly server build information including version number, build timestamp, and Go version. Use this to verify server version, check compatibility, or troubleshoot issues by confirming which version is running.

  • vmanomaly_get_deployment_sizing_profiles

    List shipped experimental deployment-sizing model/parameter profiles, target versions and CPU reference. Use to discover calibrated configurations before sizing; unavailable on older servers.

  • vmanomaly_get_metrics

    Get currently instant Prometheus-formatted self-monitoring metrics from vmanomaly server. Returns operational metrics including reader/writer performance, model execution stats, system info, and resource usage. Output is in standard Prometheus text exposition format suitable for scraping or monitoring analysis.

  • vmanomaly_get_model_schema

    Get the complete JSON schema for a UI-compatible model type returned by vmanomaly_list_models. Returns parameters, types, validation rules, defaults, and descriptions. Multivariate models are intentionally unavailable from this UI-oriented endpoint; configure them outside VMUI using documentation and validate the complete model config.

  • vmanomaly_get_server_models

    Get configured server models and their query attachments. Returns runtime model aliases, model configuration, attached queries, and model metadata from the vmanomaly server.

  • vmanomaly_get_server_queries

    Get query aliases and MetricsQL/LogsQL expressions configured on the running vmanomaly server.

  • vmanomaly_health_check

    Check the health status of the vmanomaly server

Show 6 more tools
  • vmanomaly_list_models

    List model types exposed to VMUI and other UI-oriented configuration flows. Use this before selecting a model in UI, then call vmanomaly_get_model_schema. Experimental multivariate models may be included depending on the connected server version. Use its response as the source of truth.

  • vmanomaly_read_doc_section

    Read a bounded documentation section by source URI and character offset returned by search. Follow next_offset for continuation; fetch relevant sections before relying on truncated guidance.

  • vmanomaly_search_docs

    Search vmanomaly documentation using full-text search with fuzzy matching. Returns ranked excerpts with source URIs and character offsets. Use vmanomaly_read_doc_section for additional text; excerpts are not complete documentation. Use this when you need information about model parameters, configuration syntax, troubleshooting, or feature explanations.

  • vmanomaly_timeseries_characteristics

    Profile a sampled set of time series returned by a query. Returns compact batch characteristics such as detected seasonalities, trend share, flatness/spikiness, coverage, and sampling stats. Use this before recommending a model from data rather than from a manual description.

  • vmanomaly_validate_config

    Validate a complete vmanomaly YAML configuration. Takes a full configuration object (with reader, scheduler, model, writer sections) and returns validation result with normalized config or error details. Use this to verify a complete config before deployment.

  • vmanomaly_validate_model_config

    Validate an anomaly detection model configuration before using it. Returns validation result with the normalized/validated configuration or detailed error messages if invalid. Use this after building your model config to catch configuration errors before creating a detection task with vmanomaly_create_detection_task.

Signals

Stars
11
Forks
3
Open issues
0
Last commit
Oct 15, 2026 (13 days ago)
Last release
Oct 15, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.VictoriaMetrics/mcp-vmanomaly
Version
0.5.1
Auth
API key
Packages
oci ghcr.io/victoriametrics/mcp-vmanomaly:0.5.1
License
Apache-2.0
Repository
github.com/VictoriaMetrics/mcp-vmanomaly
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from VictoriaMetrics

Cite this page

MCP Vmanomaly. Agent Mart. https://agentmart.dev/connectors/victoriametrics-mcp-vmanomaly (last updated 2026-10-24)