Pirsch Analytics MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PIRSCH_TIMEZONE | No | Timezone for analytics data. Default: UTC. | UTC |
| PIRSCH_CLIENT_ID | Yes | Your Pirsch API client ID. | |
| PIRSCH_CLIENT_SECRET | Yes | Your Pirsch API client secret. | |
| PIRSCH_TOKEN_SKEW_MS | No | Token refresh buffer in milliseconds. Default: 60000. | 60000 |
| PIRSCH_DEFAULT_DOMAIN_ID | No | Default domain ID to use if not specified in queries. Auto-detected if not set. |
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 |
|---|---|
| pirsch_list_domainsA | List safe summaries of domains available to the configured read-only Pirsch OAuth client. |
| pirsch_query_statisticsB | Read one documented Pirsch Analytics API v1 metric for an explicitly selected domain and filter. |
| pirsch_list_filter_optionsC | List supported values for one documented Pirsch Analytics API v1 filter dimension. |
| pirsch_compare_periodsA | Compare Pirsch totals and visitor series for a named or explicitly supplied pair of periods. |
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 4 tools
Each tool targets a distinct concern: listing domains, querying a metric, enumerating filter options, and comparing periods. There is no overlap or ambiguity between them.
All tools follow a consistent 'pirsch_verb_noun' pattern (list_domains, query_statistics, list_filter_options, compare_periods). The naming style is uniform and predictable.
Four tools is well-scoped for a read-only analytics server. Each tool covers a necessary high-level operation without unnecessary bloat or redundancy.
The set covers the core read-only needs: domain discovery, metric querying, filter exploration, and period comparison. A minor gap is the lack of a more comprehensive report endpoint, but the available tools can be combined to cover most scenarios.