An Eventbrite MCP server for interacting with Eventbrite's API
Four tools with complete schemas and basic descriptions, but significant gaps in parameter documentation and error guidance. All tools are READ_ONLY (good for safety), but descriptions lack actionable context for LLM selection. search_events has complex nested parameters (location object) that lack individual field descriptions. No output schemas documented. Error handling exists but does not guide recovery. Naming is clear and verb-based (search_, get_), following conventions. Average description length ~80 chars, below the 194-char baseline for A+ tools.
Get a list of all Eventbrite event categories
Get detailed information about a specific Eventbrite event
Get detailed information about a specific venue
Search for Eventbrite events based on various criteria
search_events location parameter lacks nested field descriptions. 'latitude', 'longitude', 'within' are required/optional but not documented in parameter descriptions, LLM must infer from JSON Schema alone.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., event_id from search_events to pass to get_event). Responses are inferred from code but not declared in tool definitions.
Error messages in code throw generic 'Eventbrite API error' without recovery guidance. LLM receives no hint whether to retry, ask user, or try alternative tool. Violates recovery-guide pattern.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
search_events accepts 'page' and 'page_size' but no documented limits or defaults. Unbounded page_size could cause context window exhaustion. Baseline requires pagination with limits and total count.
get_categories description is 'Get a list of all Eventbrite event categories' (47 chars), below 50-char minimum for clarity. Does not explain when to call it (e.g., 'Call before search_events to filter by category_id') or what structure it returns.