MCP CSV Analysis with Gemini AI
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Optional flag to enable verbose logging (e.g., 'true'). | |
| GEMINI_API_KEY | Yes | Your Google Gemini API key used for data analysis and reasoning. | |
| PLOTLY_API_KEY | Yes | Your Plotly API key, required for generating visualizations. | |
| PLOTLY_USERNAME | Yes | Your Plotly username, required for generating visualizations. |
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 |
|---|---|
| generate-thinkingC | Generate detailed thinking process text using Gemini's experimental thinking model |
| analyze-csvC | Analyze CSV file using Gemini's AI capabilities for EDA and data science insights |
| visualize-dataC | Generate visualizations from CSV data using Chart.js |
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 3 tools
Each tool has a clearly distinct purpose: analyze-csv focuses on data analysis and insights, generate-thinking produces text-based reasoning, and visualize-data creates charts. There is no overlap in functionality, making tool selection straightforward for an agent.
The tools follow a consistent verb-object pattern (analyze-csv, generate-thinking, visualize-data), all using kebab-case. The naming is predictable and readable, with only minor deviations like 'visualize-data' using a verb-noun structure while others use verb-ing-noun.
With only 3 tools, the server feels thin for a CSV analysis domain that could include operations like data cleaning, filtering, or exporting. While the tools cover core AI-driven tasks, the scope is limited and might require workarounds for common data workflows.
There are significant gaps in the tool surface for CSV analysis: no tools for basic operations like loading/reading CSV files, filtering data, handling missing values, or exporting results. The server relies heavily on AI and visualization without foundational data manipulation capabilities, which could lead to agent failures in typical data processing tasks.