Lightdash MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lightdash_list_projectsA | List all projects in the Lightdash organization |
| lightdash_get_projectA | Get details of a specific project |
| lightdash_list_spacesC | List all spaces in a project |
| lightdash_list_chartsA | List all charts in a project |
| lightdash_list_dashboardsA | List all dashboards in a project |
| lightdash_get_custom_metricsC | Get custom metrics for a project |
| lightdash_get_catalogC | Get catalog for a project |
| lightdash_get_metrics_catalogB | Get metrics catalog for a project |
| lightdash_get_charts_as_codeC | Get charts as code for a project |
| lightdash_get_dashboards_as_codeC | Get dashboards as code for a project |
| lightdash_get_metadataB | Get metadata for a specific table in the data catalog |
| lightdash_get_analyticsC | Get analytics for a specific table in the data catalog |
| lightdash_get_user_attributesB | Get organization user attributes |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools target distinct resources (analytics, catalog, charts, dashboards, projects), but there is potential confusion between 'get_catalog' and 'get_metrics_catalog', and between 'get_analytics' and 'get_metadata' for a specific table. Descriptions help clarify, but some overlap exists.
All tools follow a consistent 'lightdash_verb_noun' pattern, using 'get_' or 'list_' prefixes. The 'as_code' suffix in two tools is a minor deviation but still fits the pattern well.
With 13 tools covering catalog, charts, dashboards, metrics, projects, spaces, and user attributes, the number is well-scoped for a read-only analytics server. It is neither too few nor too many.
The server covers many read operations (get, list) but lacks any write tools (create, update, delete), which is a notable gap for full lifecycle management in Lightdash. Agents may need write capabilities for many workflows.