Skip to main content
Glama
ae3e

kairosdb-mcp-server

by ae3e
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KAIROSDB_URLNoKairosDB server URLhttp://localhost:8080
KAIROSDB_USERNoHTTP Basic username (optional)
KAIROSDB_PASSWORDNoHTTP Basic password (optional)

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
kairosdb_query_rangeA

Queries KairosDB for a metric's data over a relative time range (e.g. the last 24 hours).

Typical use cases:

  • "Give me the CPU usage data for server web-01 over the last 7 days"

  • "Show me the memory usage from last week"

Args:

  • metric_name: Exact KairosDB metric name

  • tags: Tag filters (e.g. {"host": ["web-01"]})

  • range_value: Duration to look back (default: 24)

  • range_unit: Unit (hours/days/weeks/..., default: hours)

  • aggregator: Optional aggregation function (avg/min/max/sum/count)

  • sampling_value / sampling_unit: Window size if aggregation is enabled

  • limit: Max number of points (default: 1000, max: 10,000)

  • response_format: "markdown" (default) or "json"

Returns: Timestamped data points with statistics (min/max/avg).

kairosdb_query_absoluteA

Queries KairosDB over a time range defined by precise ISO 8601 dates.

Use cases:

  • "Server metrics between 2024-01-01 and 2024-01-31"

  • "Analysis of a precise incident over a timestamped window"

Args:

  • metric_name: Exact metric name

  • tags: Tag filters

  • start: Start (ISO 8601, e.g. 2024-01-15T00:00:00Z)

  • end: End (ISO 8601, default: now)

  • aggregator / sampling_value / sampling_unit: Optional aggregation

  • limit: Max points (default 1000)

  • response_format: "markdown" or "json"

Returns: Timestamped points with statistics.

kairosdb_last_valueA

Retrieves the most recent value of a metric (equivalent to a real-time reading).

Use cases:

  • "What is the current CPU usage on server web-01?"

  • "Latest reading from the request latency metric"

Args:

  • metric_name: Exact metric name

  • tags: Tag filters to target a specific host

  • response_format: "markdown" or "json"

Returns: Latest known value with its timestamp.

kairosdb_aggregateA

Computes several aggregations (min, max, avg, etc.) in a single request over a relative time range.

Use cases:

  • "Give me the min/max/avg CPU usage on server web-01 over the last 7 days, hourly"

  • "Daily request latency statistics over the last 30 days"

Args:

  • metric_name: Exact metric name

  • tags: Tag filters

  • range_value / range_unit: Time range (default: 24 hours)

  • aggregators: List of functions (default: [avg, min, max])

  • sampling_value / sampling_unit: Computation window (default: 1 hour)

  • response_format: "markdown" or "json"

Returns: One series per aggregator with statistics.

kairosdb_list_metricsA

Returns all metrics (host/service series names) stored in KairosDB.

Use cases:

  • "Which metrics are available for the servers?"

  • "List all metrics starting with 'server.'"

Args:

  • prefix: Optional prefix filter (e.g. "server." to filter client-side)

  • response_format: "markdown" or "json"

Returns: List of metric names.

kairosdb_list_tag_valuesA

Returns all known values for a given tag name.

Use cases:

  • "What hosts are available?" → tag_name = "host"

  • "What environments exist?" → tag_name = "environment"

Args:

  • tag_name: Tag name (e.g. "host", "environment", "region")

  • response_format: "markdown" or "json"

Returns: List of values for this tag.

kairosdb_healthA

Checks that the KairosDB server is reachable and operational.

Use cases:

  • "Is KairosDB available?"

  • Diagnosing a connection error

Returns: "ok" or "error" status with details.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 7 tools

Disambiguation4/5

query_range/query_absolute/last_value are clearly separated by time framing, and list_metrics/list_tag_values/health serve distinct discovery and operations roles. Some overlap exists between query_range and aggregate, since both support relative ranges with aggregation, though one returns data points with optional stats and the other computes multiple aggregations.

Naming Consistency4/5

All tools share the kairosdb_ prefix and most follow a kairosdb_<operation>_<object> pattern, e.g. query_range, query_absolute, list_metrics, list_tag_values. Minor deviations like kairosdb_aggregate and kairosdb_last_value are still predictable within the overall convention.

Tool Count5/5

Seven tools is a well-scoped size for a read-only time-series database MCP server. Each tool earns its place by covering a distinct querying, discovery, or health-check need without unnecessary redundancy.

Completeness4/5

The set covers relative and absolute time-range queries, latest-value reads, aggregation, metric discovery, tag-value discovery, and health checks. Minor gaps like listing tag keys or write/delete operations are acceptable for a read-oriented query server.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources