Grips Intelligence MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GRIPS_API_KEY | Yes | Your Grips API token (sent as the grips-api-key header). | |
| GRIPS_DEFAULT_COUNTRY | No | US, GB, or DE. Defaults to US if unset or invalid. | US |
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 |
|---|---|
| grips_get_domain_performanceA | Returns a monthly timeseries of revenue, transactions, sessions, ad cost, AOV, CR, and CPC for one or more domains over a date range. Use this for anything like 'how did adidas.com perform in Q1 2024' or 'compare nike.com and puma.com session volume YoY'. Defaults to markdown output; pass format='json' for structured data. |
| grips_get_daily_performanceA | Returns a daily timeseries of revenue, transactions, and sessions for one or more domains. Useful for spike/dip detection, promo windows, and day-of-week patterns. Note: Grips only offers daily data for a subset of domains — smaller sites often return empty. Defaults to markdown output. |
| grips_get_channelsA | Returns revenue, sessions, transactions, CR, and AOV broken out by marketing channel (Organic Search, Paid Search, Direct, Referral, Social) for one or more domains. Use this to understand channel mix, evaluate paid-vs-organic balance, or spot a channel shift over time. Response includes both a monthly timeseries and an aggregated roll-up. |
| grips_get_adwordsA | Returns paid-media spend, ad clicks, and CPC for one or more domains — monthly timeseries plus an aggregated roll-up. Use this to evaluate paid-spend trends, auction-cost inflation, or total investment in paid search. |
| grips_get_devicesA | Returns device-level revenue, sessions, transactions, CR, and AOV for one or more domains aggregated over a date window. Use this to understand where a competitor's traffic and conversions come from — mobile vs desktop split, AOV by device, etc. |
| grips_compare_domainsA | Fetches per-domain performance in parallel and returns a leaderboard ranked by the chosen metric (revenue, sessions, AOV, etc.). Per-domain failures are captured in an |
| grips_raw_queryA | Sends an arbitrary Grips GraphQL-like query and returns the raw JSON response. Use this only when the purpose-built tools (domain performance, channels, adwords, devices, daily, compare) don't cover what you need. The response is returned verbatim with no formatting — you are responsible for parsing it. |
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 7 tools
Each tool targets a distinct data dimension (domain performance, adwords, channels, devices, daily performance, comparison, raw query) with clear separation. No two tools have overlapping purposes.
All tools follow a consistent `grips_<verb>_<noun>` pattern in snake_case, with verbs like 'get' and 'compare', and a single exception 'raw_query' still fits the pattern. No mixing of conventions.
With 7 tools, the set is well-scoped for an analytics server covering multiple metrics and dimensions. Not too few to be limited, not too many to be overwhelming.
Core analytics needs are covered, and the raw query tool fills potential gaps. Minor missing areas like product-level data exist, but the surface is largely complete for the stated purpose.