mcp-csv-analyst
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| csv_describeB | Load a CSV file and return its schema, row count, and column statistics |
| csv_filterB | Filter CSV rows by a column condition. Returns matching rows as JSON. |
| csv_aggregateB | Compute an aggregate (sum, avg, min, max, count, median) on a numeric column |
| csv_group_byC | Group rows by a column and compute an aggregate on another column |
| csv_sampleB | Get a sample of rows from a CSV file |
| csv_uniqueB | Get unique values in a column with their counts |
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 6 tools
Each tool has a clearly distinct purpose with no ambiguity: describe for metadata, filter for row selection, sample for sampling, unique for value analysis, aggregate for column calculations, and group_by for grouped aggregations. The descriptions make it easy to differentiate between similar-sounding tools like aggregate and group_by.
All tools follow a perfect 'csv_verb' pattern with consistent snake_case naming. The verbs (describe, filter, sample, unique, aggregate, group_by) are all action-oriented and clearly indicate what each tool does, creating a predictable and readable naming convention throughout.
Six tools is an ideal number for a CSV analysis server - enough to cover essential operations without being overwhelming. Each tool serves a distinct, valuable purpose in the data analysis workflow, making the count well-scoped and appropriate for the domain.
The toolset covers most essential CSV analysis operations well: inspection (describe), filtering (filter), sampling (sample), value analysis (unique), and aggregation (aggregate, group_by). A minor gap exists in transformation operations (like sorting, merging, or column manipulation), but agents can work around this with the provided tools for core analysis tasks.