MCP Analytics
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_ANALYTICS_API_KEY | No | API key from app.mcpanalytics.ai (free signup) |
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 |
|---|---|
| aboutC | Get platform info, pricing, usage stats, or documentation. |
| discover_toolsA | Find analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools. |
| tools_schemaB | Get JSON schema for a tool — column_mapping and module_parameters required before tools_run. |
| tools_runC | Execute an analysis tool. Returns a shareable interactive HTML report URL. |
| tools_infoA | Get detailed information about a specific analysis tool — use cases, assumptions, data requirements. |
| datasets_uploadA | Generate a secure upload token for CSV files. Returns UUID + curl command for the user. |
| datasets_listA | List and search uploaded datasets with fuzzy matching. |
| datasets_readB | Read dataset contents — preview rows, columns, and types. |
| datasets_downloadA | Generate a single-use download token for securely downloading datasets. |
| datasets_updateC | Update dataset metadata — name, description, tags, visibility. |
| connectors_listA | List available data connectors — GA4, Google Search Console, and more. |
| connectors_queryB | Pull live data from a connected source using connector:// URIs. |
| reports_listC | List analysis reports with metadata. |
| reports_searchB | Search reports by job ID, tool name, or keyword. |
| reports_viewB | View a specific report by processing ID. |
| report_cardsC | Get individual card data from a report for rendering. |
| agent_advisorC | Conversational AI that guides analysis and interprets results. |
| billingA | Check credit balance, subscription status, or open billing portal. |
| module_requestB | Request a custom analysis module to be built for your use case. |
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 19 tools
Most tools are grouped by resource and action, but there is some overlap: reports_view vs reports_list vs report_cards could be confused, and datasets_read vs datasets_download may seem similar at first glance. tools_info, discover_tools, and agent_advisor also all occupy a 'help me use the system' space that requires careful reading.
The naming has a recognizable pattern for the main clusters (datasets_*, reports_*, connectors_*, tools_*), but it is not consistently applied: report_cards and module_request are noun-only, while billing and about are bare nouns. The pattern is predictable within each domain but not uniform across the server.
19 tools is on the heavy side, but the platform covers datasets, connectors, analysis tools, reports, billing, and system info, so the breadth is somewhat justified. Still, some clusters could be consolidated (e.g., reports_list vs reports_search) to reduce cognitive load.
The main workflow — upload/read datasets, query connectors, discover and run tools, and view reports — is well covered. The primary gap is the lack of delete/removal operations for datasets and reports, plus no obvious connector setup or management tools, but most core analysis workflows are supported.