Portfolio Data Analytics 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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| load_csvA | Register a dataset from CSV text. Returns the inferred schema. Args: name: a unique name for the dataset. csv_text: raw CSV content (comma-separated, first row is header). |
| list_datasetsA | List all registered datasets with their schema. |
| summaryC | Return summary statistics for a numeric column or whole dataset. Args: name: the dataset name. |
| filter_rowsA | Filter rows where Args: name: the dataset name. column: the numeric column to filter on. operator: one of '>', '<', '>=', '<=', '==', '!='. value: the threshold. |
| top_rowsA | Return the top-N rows sorted by Args: name: the dataset name. column: the column to sort by. n: how many rows to return (default 5). |
| correlationA | Return the Pearson correlation between two numeric columns. Args: name: the dataset name. col_a: first numeric column. col_b: second numeric column. |
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 targets a distinct data operation: loading, listing, summarizing, filtering, sorting, and correlation. There is a slight potential for overlap between summary and correlation, but they are clearly differentiated by scope (full dataset vs. pairwise columns).
All tool names follow a consistent verb_noun pattern (load_csv, list_datasets, summary, filter_rows, top_rows, correlation). The naming is clear, predictable, and uses lowercase with underscores uniformly.
With 6 tools, the server is well-scoped for a portfolio data analytics use case. Each tool serves a specific, essential analytic function without unnecessary bloat or redundancy.
The tool set covers basic data loading and exploration (summary, filtering, sorting, correlation) but lacks key operations such as grouping/aggregation, joining datasets, or data transformation (e.g., adding columns). This leaves notable gaps for a comprehensive analytics workflow.