serve-delivery-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEOCODER | No | Geocoder to use: nominatim (OpenStreetMap) or none (caller supplies lat/lng). | nominatim |
| LOG_LEVEL | No | Log level: debug, info, warn or error. | info |
| SERVE_ENV | No | Runtime environment: mock, sandbox or production. | mock |
| SERVE_API_KEY | No | Serve API key sent as X-API-Key. Required for sandbox/production. | |
| SERVE_BASE_URL | No | Override the Serve API base URL, e.g. a different mock port. Must be https outside mock mode. | |
| SERVE_PARTNER_ID | No | Serve partner ID. Required for sandbox/production. | ptnr_mock |
| GEOCODER_USER_AGENT | No | Identifying User-Agent for Nominatim, including contact info. | |
| SERVE_MAX_FEE_CENTS | No | Hard cap per delivery in cents. | 1500 |
| SERVE_ALLOW_PRODUCTION | No | Must be true to use production. | false |
| SERVE_REQUEST_TIMEOUT_MS | No | Per-request timeout in milliseconds. | 15000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tools for booking sidewalk robot deliveries via the Serve Robotics API. Workflow: get_delivery_quote → show the user the fee, ETA and addresses → get explicit approval → dispatch_robot with confirmed=true → track_delivery → unlock_robot_bin at dropoff. Never dispatch without the user's explicit approval of the quoted fee.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_robot_availabilityA | Count delivery robots on duty near a location. Use this to check whether Serve operates in an area before quoting a delivery. |
| get_delivery_quoteA | Price and ETA for a robot delivery from pickup to dropoff. Reserves nothing. Quotes expire after about 5 minutes and can be used once. Always show the fee, ETA and both resolved addresses to the user and get their explicit approval before calling dispatch_robot. |
| dispatch_robotA | Send a robot to fulfil a quote from get_delivery_quote. This creates a real delivery and incurs the quoted fee (outside mock mode). Only call it after the user has seen the fee and addresses and explicitly said yes; set confirmed=true only in that case. Pickup and dropoff are taken from the quote and can't be changed. |
| track_deliveryB | Current status, robot position and ETAs for a delivery. |
| list_deliveriesA | List deliveries, newest first. Defaults to active deliveries only. |
| cancel_deliveryA | Cancel a delivery that hasn't finished. Confirm with the user first; a canceled delivery can't be resumed. |
| unlock_robot_binA | Open the robot's cargo bin so the recipient can collect the items. Only works once the robot has arrived at the dropoff. |
| get_delivery_routeB | The robot's planned route for a delivery: distance per leg, and optionally the GeoJSON geometry for mapping. |
| simulate_delivery_progressA | Testing only (mock/sandbox): move a simulated delivery to a later stage, or reject it with a reason, to demo the full lifecycle. |
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 9 tools
Each tool maps to a distinct step in the delivery lifecycle (quote, dispatch, track, route, unlock, cancel, list, availability), so misselection is unlikely. Minor overlap exists between track_delivery and get_delivery_route, and between cancel_delivery and simulate_delivery_progress's reject action, but descriptions clarify the boundaries.
All nine tools follow a strict snake_case verb_noun convention (get_delivery_route, check_robot_availability, dispatch_robot, unlock_robot_bin, etc.). Verbs are chosen consistently for their operation type (get/list/check vs. dispatch/cancel/unlock).
Nine tools is well within the ideal 3-15 range and each earns its place by covering a distinct lifecycle operation. Nothing feels padded or missing from a count perspective.
The surface covers the full flow: availability check, quote, dispatch, track, route, unlock bin, cancel, list, plus a mock simulator for testing. Gaps are minor—no way to fetch a single delivery's full detail/history by ID or modify an in-flight delivery's dropoff.