GreptimeDB MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GREPTIMEDB_HOST | No | Database host | localhost |
| GREPTIMEDB_PORT | No | Database MySQL port | 4002 |
| GREPTIMEDB_USER | No | The database username | root |
| GREPTIMEDB_DATABASE | No | The database name | public |
| GREPTIMEDB_PASSWORD | No | The database password | |
| GREPTIMEDB_TIMEZONE | No | The session time zone | UTC |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_sqlA | Execute SQL query against GreptimeDB. Please use MySQL dialect. |
| describe_tableA | Get a table profile: schema, semantic metadata, sample rows, and guidance. |
| health_checkA | Check GreptimeDB connection status and server version. |
| execute_tqlC | Execute TQL query for time-series analysis. TQL is PromQL-compatible - use standard PromQL syntax. |
| query_rangeC | Execute time-window aggregation query using GreptimeDB's RANGE query syntax. |
| explain_queryC | Analyze SQL or TQL query execution plan. |
| list_pipelinesC | List all pipelines or get details of a specific pipeline. |
| create_pipelineC | Create a new pipeline in GreptimeDB. |
| dryrun_pipelineA | Test a pipeline with sample data without writing to the database. |
| delete_pipelineB | Delete a specific version of a pipeline from GreptimeDB. |
| list_dashboardsA | List all Perses dashboard definitions stored in GreptimeDB. |
| create_dashboardC | Create or update a Perses dashboard definition in GreptimeDB. |
| delete_dashboardC | Delete a Perses dashboard definition from GreptimeDB. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| schema_design_advisor | Schema and index design advisor for GreptimeDB tables. |
| trace_analysis | Distributed trace analysis for OpenTelemetry spans in GreptimeDB. |
| ingestion_troubleshooting | Troubleshoot GreptimeDB ingestion issues across OTLP, Prometheus, Loki, SQL, and pipelines. |
| observability_correlation | Correlate GreptimeDB metrics, logs, and traces across a shared time window. |
| query_performance_tuning | Tune GreptimeDB SQL, TQL, and RANGE queries using execution plans and table metadata. |
| metrics_analysis | SQL and RANGE analysis for existing GreptimeDB time-series tables. |
| pipeline_creator | Generate GreptimeDB pipeline YAML configuration from log samples. |
| table_operation | Table diagnostics: schema, region health, storage, and cluster metadata for GreptimeDB. |
| log_pipeline | Log analysis with full-text search and aggregation in GreptimeDB. |
| promql_analysis | PromQL-style queries using GreptimeDB TQL EVAL syntax. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
All tools have clearly distinct purposes: dashboard management, pipeline management, SQL/TQL queries, health check, and table description. No overlaps or ambiguity.
All tool names follow a consistent verb_noun pattern (e.g., create_dashboard, delete_pipeline, execute_sql). The naming convention is uniform and predictable.
With 13 tools, the set is well-scoped for a time-series database MCP server. It covers essential operations without being excessive or sparse.
The tool surface covers CRUD for dashboards, CRD for pipelines (missing update/transform), querying (SQL, TQL, range), and health check. Minor gap in pipeline update, but mostly complete.