dataville-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATAVILLE_API_KEY | Yes | Your Dataville API key, obtainable from the Dataville dashboard | |
| DATAVILLE_API_BASE_URL | No | Optional base URL for the Dataville API; set to http://localhost:5000 for local development | https://api.dataville.com |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_dataville_sourcesA | List the data sources available through Dataville's search_dataville tool. |
| search_datavilleA | Query one of Dataville's data sources (see list_dataville_sources for valid source names) with a keyword string and optional query params. |
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 2 tools
The two tools have clearly distinct purposes: one lists available data sources, the other queries a specific source. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern with the 'dataville' prefix ('list_dataville_sources', 'search_dataville'), making them predictable and easy to understand.
With only 2 tools, the server is severely under-scoped for a data platform. While listing and searching are core, many essential operations (e.g., adding/removing sources, metadata exploration) are missing, making the count feel inadequate.
The tool surface is extremely bare. Missing lifecycle operations for sources, lack of search result pagination or filtering, and no way to inspect source schemas or metadata. Agents will hit dead ends quickly.