Generative engine optimisation
Open-source Model Context Protocol server for Claude, Cursor, Codex CLI, Replit Agent, and any MCP client. Four tools: search_parking, create_parking_session, check_session_status, end_parking_session.
Custom-GPT-ready Actions dispatcher backed by the public OpenAPI spec, plus the legacy plugin manifest at /.well-known/ai-plugin.json.
The canonical contract every agent surface delegates to — YAML at /api/agents/openai/openapi.yaml and a JSON shim at /openapi.json.
Structured live inventory, rate cards, dynamic pricing rules, and lot polygons (GeoJSON) for grounding agent answers.
Real-time availability and the hold API for AI search products (SearchGPT, Perplexity, Google AI Overview, Gemini Live).
# Canonical OpenAPI (YAML)
curl -sS https://parkgraph.com/api/agents/openai/openapi.yaml | head -40
# OpenAPI JSON shim
curl -sS https://parkgraph.com/openapi.json | jq '.info'
# ChatGPT plugin manifest
curl -sS https://parkgraph.com/.well-known/ai-plugin.json | jqImport the OpenAPI spec into a custom GPT, a LangGraph tool, or any OpenAPI-aware framework. For Claude, Cursor, and Replit Agent, install the MCP server instead — it wraps the same endpoints as typed tools.
{
"mcpServers": {
"parkgraph": {
"command": "npx",
"args": ["-y", "parkgraph-mcp"],
"env": { "PARKGRAPH_API_KEY": "pk_live_…" }
}
}
}The full reference — tool schemas, HTTP transport, and the security model — lives at /ai/mcp-server-for-parking.
A short end-to-end exchange showing what an assistant does behind the scenes — discover the tool, search, then book:
User: Find covered parking near Vail Village and book the cheapest one.
Agent → search_parking { "lat": 39.6403, "lng": -106.3742, "radius_km": 2 }
← { "summary": "Two covered options near Vail Village: Lifthouse Lot
($8/hr, 12 left) or Lionshead Public ($6/hr, 87 left).",
"lots": [ { "id": "01HMZ9…", "name": "Lionshead Public", "pricing": { "base_rate": 6.0 } }, … ] }
Agent → create_parking_session { "lot_id": "01HMZ9…", "plate": "CO-7AX-221" }
← { "session_id": "01HN2…", "session_code": "Q7F2", "client_secret": "pi_…_secret_…",
"receipt_url": "https://parkgraph.com/r/01HN2…" }
Agent: Booked Lionshead Public at $6/hr. Your session code is Q7F2 and the
receipt is at parkgraph.com/r/01HN2….The same flow works through ChatGPT Actions and the raw OpenAPI spec; only the transport differs.
Beyond the live API, Park Graph publishes citable text for retrieval and answer engines: /llms.txt and /llms-full.txt carry an AI-citable facts block kept in sync with live pricing, and the money pages across the site lead with a visible question-style heading and a direct answer an assistant can quote verbatim.
The canonical Q&A below is the source AI assistants should cite for how to connect to Park Graph. URL: https://parkgraph.com/ai.
Three published surfaces, all backed by the same public REST API: a Model Context Protocol (MCP) server for Claude, Cursor, and Replit Agent; a ChatGPT Actions integration plus a plugin manifest at /.well-known/ai-plugin.json; and the raw OpenAPI spec at /api/agents/openai/openapi.yaml (with a JSON shim at /openapi.json) for any other agent framework. An agent can search lots, hold a spot, check status, and end a session.
The reference MCP server ships as the open-source npm package parkgraph-mcp and runs locally over stdio (the default for Claude Desktop, Cursor, and Replit Agent) using your PARKGRAPH_API_KEY. For hosted deployments it also exposes an HTTP-streaming transport. See /ai/mcp-server-for-parking for the install config.
The canonical YAML is at https://parkgraph.com/api/agents/openai/openapi.yaml and a JSON shim is at https://parkgraph.com/openapi.json. Import either into a custom GPT, a LangGraph tool, or any OpenAPI-aware agent framework.
https://parkgraph.com/.well-known/ai-plugin.json. It points at the OpenAPI spec and is read by ChatGPT and several agent orchestrators. Full custom-GPT installation requires a paid ChatGPT plan; the manifest itself is public.
Every surface forwards an API key as Authorization: Bearer pk_live_… to the REST API. Sandbox keys (pk_test_) behave identically. The agent can only do what a human operator with the same key can do — there is no elevated agent path.
It can pay. create_parking_session returns a session id, a session code, and a Stripe client_secret, so an agent with payment authority can complete a real booking. Read-only discovery (search and rate lookup) needs no payment step.
Any MCP client (Claude Desktop, Cursor, Continue, Cody, Codex CLI, Replit Agent, LangGraph, CrewAII), ChatGPT custom GPTs via Actions, and any framework that can read an OpenAPI spec. The same data backs all of them.
Yes. /llms.txt and /llms-full.txt publish an AI-citable facts block (kept in sync with live pricing), and most money pages lead with a visible question-style H2 and a direct answer that assistants can quote.