Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Local Rides and Deliveries API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffleetengine.googleapis.com%2Ffleet-engine" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffleetengine.googleapis.com%2Ffleet-engine" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Local Rides and Deliveries API.
Create on-demand ride trips and search a provider's trips
Register, update, list, and search vehicles and update their attributes
Provision delivery vehicles and list them for last-mile fleets
Create delivery tasks individually or in batches and list them
Patch a task's state as a delivery progresses
GET STARTED
Report billable trips for usage accounting
Patterns agents use Local Rides and Deliveries API for, with concrete tasks.
★ Agent-Driven Dispatch
An AI agent connected through Jentic can run dispatch for a rides-and-deliveries provider without a developer wiring Google OAuth and the provider resource paths. The agent registers a vehicle, searches for available vehicles for a request, and creates the trip, keeping the fleet assigned. Jentic injects the OAuth credential at call time so it never reaches the agent.
Search for available vehicles for a provider, create a trip for the ride request, and confirm the trip was created
Last-Mile Delivery Task Management
Delivery operators can push a day's stops into Fleet Engine and track them as drivers progress. The agent batch-creates delivery tasks, assigns them against delivery vehicles, and patches each task's state as it is completed. This keeps the operational record current for a last-mile fleet.
Batch-create delivery tasks for a route, then patch a task's state to completed as the driver finishes it
Fleet Vehicle Registration
Providers onboarding drivers register each vehicle and keep its attributes current. The agent creates a vehicle, updates its attributes, and lists the provider's vehicles to confirm the roster. This keeps the fleet inventory accurate as drivers join and leave.
Create a vehicle for a provider, update its attributes, then list the provider's vehicles to confirm it is registered
16 endpoints — the google fleet engine local rides and deliveries api manages the vehicles, trips, and delivery tasks behind on-demand ride and last-mile delivery operations.
METHOD
PATH
DESCRIPTION
/v1/{parent}/trips
Create a trip
/v1/{parent}/trips:search
Search trips for a provider
/v1/{parent}/vehicles
Register a vehicle
/v1/{parent}/vehicles
List vehicles for a provider
/v1/{parent}/tasks
Create a delivery task
/v1/{parent}/deliveryVehicles
Provision a delivery vehicle
/v1/{name}:report
Report a billable trip
/v1/{parent}/trips
Create a trip
/v1/{parent}/trips:search
Search trips for a provider
/v1/{parent}/vehicles
Register a vehicle
/v1/{parent}/vehicles
List vehicles for a provider
/v1/{parent}/tasks
Create a delivery task
/v1/{parent}/deliveryVehicles
Provision a delivery vehicle
/v1/{name}:report
Report a billable trip
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Fleet Engine by hand means setting up Google OAuth 2.0 on the cloud-platform scope, refreshing tokens, and threading the provider resource name through every path yourself. Through Jentic you install once, import Fleet Engine from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Fleet Engine puts the provider resource name in the URL path, so a rule can pin your agent to one provider and the operations you pick, such as creating trips and listing vehicles. You choose which operations it may call, so destructive ones like deleting a vehicle are not included unless you add them.
Credential isolation
Your Google OAuth credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a trip for an on-demand ride' or 'batch-create delivery tasks', and Jentic returns the matching Fleet Engine operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Local Rides and Deliveries API through Jentic.
What authentication does the Fleet Engine API use?
Per its OpenAPI spec, the Fleet Engine API uses Google OAuth 2.0, with the cloud-platform scope, in either the implicit or authorization-code flow. Through Jentic the credential is stored encrypted by your own instance and injected at call time, so it never reaches the agent.
Is there a Fleet Engine MCP server?
You don't need an MCP server to give your agent Fleet Engine. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls operations like creating a trip or batch-creating delivery tasks on demand, without loading another server's tool definitions into its context.
Can I limit what my agent is allowed to do with Fleet Engine?
Yes. Fleet Engine puts the provider resource name in the URL path, so a rule can pin your agent to one provider and the operations you pick, such as creating trips and listing vehicles, so it cannot delete a vehicle unless you add that operation, and every call it makes is logged. This matches a dispatch bot that should assign work without destructive power.
Can I manage delivery tasks with the Fleet Engine API?
Yes. Create delivery tasks individually or in batches, list them for a provider, and patch each task's state as the delivery progresses. You provision delivery vehicles the tasks are carried out against.
What are the rate limits for the Fleet Engine API?
The OpenAPI spec does not specify rate limits. Check the Google Maps Platform documentation at https://developers.google.com/maps/documentation/mobility for current Fleet Engine quotas before scaling up dispatch volume.
How do I dispatch a ride with the Fleet Engine API through Jentic?
Search Jentic for 'create a trip for an on-demand ride', which returns the vehicle search and trip creation operations with their input schemas. The agent finds an available vehicle, creates the trip, and confirms it, with your stored OAuth credential injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create and search trips, register and update vehicles and delivery vehicles, create and patch delivery tasks, and report billable trips for Google Fleet Engine ride and delivery fleets. Authorized with Google OAuth 2.0.
Use for: I need to create a trip for an on-demand ride, Register a new vehicle for a provider, Search for available vehicles near a location, Create a batch of delivery tasks for a route
Not supported: Does not render maps, geocode addresses, or compute driving routes. Use for Fleet Engine ride and delivery fleet operations only.
The Google Fleet Engine Local Rides and Deliveries API manages the vehicles, trips, and delivery tasks behind on-demand ride and last-mile delivery operations. It creates and searches trips, registers and updates vehicles and their attributes, provisions delivery vehicles, and creates and lists delivery tasks individually or in batches. A task can be patched as a delivery progresses, and billable trips can be reported for usage accounting. Access is authorized with Google OAuth 2.0 on the cloud-platform scope.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>