Categories › AI & Agents › Multi-agent, orchestration & workflows
MCP server for valet parking: 789 US operators across 31,186 cities. 7 tools. No auth.
Remote server: your requests and data go to api.getvaletparking.com. Claude Code: claude mcp add --transport http valet-parking-directory https://api.getvaletparking.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
valet_list_services — List the 9 canonical valet service slugs with display name and category. Use this when an agent needs to validate or discover the supported valet_get_operator — Get the full operator profile by slug including address, phone, listing URL, website (paid listings only), services, venues_served, FAQs, anvalet_search_cities — Search the cities directory by name prefix with population-ranked results. Use this when an agent needs to resolve a partial city name into valet_find_operators_in_city — List valet operators serving a city slug plus state slug, optionally narrowed by service. Use this when an agent has a city already disambigvalet_search_by_service_and_city — Search valet operators by service slug plus city slug across all matching states. Use this when an agent has both a service slug and a city valet_find_nearest_operators — List nearest valet operators within a 100-mile cap of a coordinate, optionally narrowed by service. Use this when a user is in a city with nvalet_find_operators_near — Find valet operators within a given radius of a coordinate, ranked by listing tier then distance. Use this when you have a coordinate and anvalet_request_quote — Submit a valet parking quote request to the operators serving a US city. Use this when a person has asked you to arrange valet and has givenNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.