Disney Parks MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MOUSE_MCP_DB_PATH | No | SQLite database path | ~/.cache/mouse-mcp/disney.db |
| MOUSE_MCP_TIMEOUT | No | Request timeout in ms | 30000 |
| MOUSE_MCP_HEADLESS | No | Run Playwright in headless mode | true |
| MOUSE_MCP_LOG_LEVEL | No | Log level: DEBUG, INFO, WARN, ERROR | INFO |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_parksA | List all Disney parks with their IDs, names, and locations. Returns Walt Disney World (wdw) and Disneyland Resort (dlr) with their theme parks. Use park IDs from this response when filtering attractions or dining. |
| find_attractionsA | Find attractions at Disney parks with filters. Returns ride metadata including height requirements, Lightning Lane status, thrill level, and single rider availability. Use list_parks first to get valid destination and park IDs. |
| find_diningA | Find dining locations at Disney parks with filters. Returns restaurant metadata including service type, meal periods, cuisine, price range, and reservation requirements. Use list_parks first to get valid destination and park IDs. |
| searchA | Search for Disney entities by ID or name. Uses fuzzy matching for name queries like 'Space Mountain' or 'Be Our Guest'. For conceptual queries like 'thrill rides' or 'romantic dinner', use discover instead. |
| discoverA | Discover Disney experiences using natural language. Uses semantic search to find entities matching concepts like 'thrill rides for teenagers', 'romantic dinner spots', or 'character breakfast'. Requires initialize to be run first. For exact name lookups, use search instead. |
| statusA | Get server health status, session state, and cache statistics. Useful for debugging data freshness and connectivity issues. |
| initializeA | Initialize the server by loading all Disney park data and generating embeddings for semantic search. Call this once before using discover for meaning-based queries. Returns statistics about loaded entities and embedding generation progress. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| plan-park-day | Plan a perfect day at a Disney theme park with personalized recommendations for attractions, dining, and timing |
| dining-scout | Find the perfect Disney dining experience based on cuisine, atmosphere, and special occasions |
| thrill-finder | Find attractions matching your thrill tolerance and preferences across Walt Disney World |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no significant overlap. For example, 'discover' handles semantic/conceptual queries, 'search' handles exact name lookups, and tools like 'find_attractions' and 'find_dining' target specific resource types. The descriptions explicitly differentiate between similar tools (e.g., 'discover' vs. 'search'), preventing agent confusion.
Most tools follow a consistent verb_noun pattern (e.g., 'find_attractions', 'find_dining', 'list_parks', 'search'), but 'discover' and 'initialize' deviate slightly by using single verbs without nouns. However, these deviations are minor and still readable, maintaining overall clarity without chaotic mixing of conventions.
With 7 tools, the count is well-scoped for the Disney parks domain, covering core operations like data initialization, park listing, attraction/dining discovery, and health checks. Each tool earns its place by addressing specific needs, such as semantic search, exact lookups, and filtered queries, without being overly sparse or bloated.
The tool surface covers essential CRUD-like operations for the domain, including initialization, listing, searching, and filtering for attractions and dining. Minor gaps exist, such as no explicit update or delete tools for dynamic data (e.g., ride wait times), but agents can work around this using the provided tools for discovery and status checks.