MCP server for Kenya transport — matatu routes, NTSA services, boda-boda licensing, freight logistics, and passenger rights. 5 tools.
All 5 tools have descriptions and basic schemas with typed parameters. However, descriptions are generic and lack actionable context for LLM selection. Parameter descriptions are minimal (e.g., 'Origin town or location' provides no format guidance). No output schemas documented. All tools marked DEMO with no guidance on when/how to use them in production. Tool names lack action verbs (matatu_route_finder, ntsa_services_guide are noun-heavy). No error handling guidance, no pagination for list-like results, no recovery paths. Schemas present but sparse, most parameters lack constraints (enums, ranges, patterns). This is typical community-server quality: functional but not LLM-optimized.
Boda boda (motorcycle taxi) licensing requirements in Kenya. DEMO.
Freight logistics options for Kenya SMEs. DEMO.
Find matatu routes between Kenyan towns. DEMO.
NTSA services guide: driving licence, vehicle inspection, permits. DEMO.
Passenger rights for Kenya public transport. DEMO.
Tool names lack action verbs. 'matatu_route_finder', 'ntsa_services_guide', 'boda_licensing_guide' are noun-heavy and do not signal what action the LLM should expect. Should be 'search_matatu_routes', 'get_ntsa_service_info', 'get_boda_licensing_requirements'.
No output schemas documented. LLMs cannot plan downstream calls or extract structured data. Each tool returns a dict but the schema (fields, types, required keys) is invisible to the agent.
Parameter descriptions are generic and lack constraints. 'Origin town or location' does not specify format, valid values, or examples. No enums for service types (ntsa_services_guide accepts free-form 'service' string instead of enum: driving_licence|vehicle_inspection|psv_licence|transfer_ownership).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
All tools marked 'DEMO' with no guidance on production readiness, data freshness, or fallback behavior. Descriptions state 'DEMO data only' but do not explain when/how to use these tools in real workflows or how to validate results.
No error handling or recovery guidance. Tools return hardcoded demo data with no validation, no error cases, and no guidance for LLMs on what to do if a lookup fails or data is stale.