Agentic Travel Recommendations API
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| get_member_profileA | Retrieves a member profile including loyalty tier, partner, and travel history. Use this to understand who the member is before making recommendations. |
| get_recommendationsA | Returns personalized travel recommendations for a member, filtered by partner rules including category exclusions and recommendation caps. Always call get_member_profile first. |
| list_membersA | Returns all available members in the system. Use this to discover valid member IDs. |
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 3 tools
Each tool serves a distinct purpose: list_members discovers valid IDs, get_member_profile provides detailed member context, and get_recommendations returns the actual recommendations. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun snake_case pattern: list_members, get_member_profile, get_recommendations. The use of 'list' for collection retrieval and 'get' for single-item retrieval is a standard and predictable convention.
With exactly 3 tools, the server is minimal but well-scoped. Each tool is necessary and supports the core workflow of discovering members, understanding their profile, and generating recommendations. This fits comfortably within the ideal 3-15 range.
The tool surface fully covers the recommendations domain: listing all members, fetching member profiles, and generating personalized recommendations. There are no obvious dead ends or missing operations for the stated purpose.