MCP DataFrame QA
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_dataframeA | Answer a natural-language question about the dataframe. |
| execute_analysis_planC | Execute a validated, read-only dataframe analysis plan. |
| preview_dataframeC | Return a capped preview of the dataframe. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask_dataframe | |
| explain_dataframe |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: executing a plan, previewing data, and answering natural language queries. There is no overlap or ambiguity.
All tool names follow a consistent verb_noun pattern with snake_case, starting with a verb and clearly indicating the action.
With only 3 tools, the server is somewhat minimal but still reasonable for focused dataframe QA. The count is on the lower end but not inappropriate.
The tools cover execution of analysis plans, preview, and query, but lack basic data exploration features like listing columns or summary statistics, which are notable gaps for a QA server.