Exposes Kashmir Tour Packages Taxi (fleet, routes, tour packages, booking enquiries) to AI assistants via the Model Context Protocol (MCP). Endpoint: /wp-json/kashmir-mcp/v1/mcp
Server exposes 7 tools with basic schemas and descriptions. All tools have non-empty descriptions (avg ~120 chars) and input schemas with type definitions. However, descriptions lack LLM-optimization guidance (no WHEN to use, no prerequisites, no recovery hints). Parameters are minimally described. Output schemas are not documented. Error handling is absent, no guidance on retryability, user-fixable vs fatal errors, or recovery paths. Tool composition is reasonable (single responsibility), but missing pagination for list_taxi_fleet and search_tour_packages. No tool annotations (readOnlyHint/destructiveHint). create_booking_enquiry is WRITE but lacks confirmation/dry-run pattern.
Creates a new booking enquiry with traveller details, travel dates, vehicle preferences, and special requirements. Returns confirmation with enquiry ID.
Returns business information including name, website, phone, WhatsApp, email, address, hours, founding year, rating, coverage areas, and services offered.
Returns detailed information about a specific tour package including itinerary, inclusions, exclusions, pricing, and booking details.
Returns route information including distance in kilometers, estimated drive time, and union taxi notes for specified origin and destination.
Returns the complete taxi fleet with details including vehicle name, seating capacity, daily rates (AC and non-AC), vehicle class, and URL to vehicle details page.
Searches tour packages by destination, duration, or theme. Returns matching packages with names, descriptions, and details.
No output schemas documented. LLMs cannot predict response structure, forcing them to guess field names for downstream tool calls or data extraction.
Descriptions lack LLM-optimization: no WHEN to use guidance, no prerequisites, no recovery hints. E.g., search_tour_packages says 'Searches tour packages' but not when to call it vs get_package_details, or what to do if no results match.
create_booking_enquiry (WRITE tool) lacks confirmation/dry-run pattern. Agents can accidentally create duplicate bookings on retry without explicit confirmation step.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 62 | 2026-07-28+ | v2 |
Searches travel guides and tips for Kashmir and Ladakh destinations. Returns matching guides with descriptions and content.
list_taxi_fleet and search_tour_packages lack pagination (limit, offset, total_count). Returning all items at once risks context window exhaustion and wastes tokens.
No error handling guidance. Tools return no recovery hints (e.g., 'Route not found. Try search_tour_packages to find valid destinations'). Agents cannot self-correct on failures.