For Agents
Programmatically reverse geocoding, search for addresses. Covers 2 operations with apiKey authentication.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PlaceKit API Reference, 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%2Fplacekit.co%2Fplacekit" | 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%2Fplacekit.co%2Fplacekit" | 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 PlaceKit API Reference API.
Reverse geocoding
Search for addresses
Access PlaceKit API Reference resources via REST API
GET STARTED
Use for: I need to reverse geocoding, I want to for addresses, I need to access PlaceKit API Reference programmatically, I want to integrate PlaceKit API Reference into my workflow
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
PlaceKit OpenAPI Specifications ([repository](https://github.com/placekit/api-reference)). The API exposes 2 endpoints secured with apiKey authentication.
Patterns agents use PlaceKit API Reference API for, with concrete tasks.
★ Developer Tools Operations
Use the PlaceKit API Reference to perform developer tools operations programmatically. The API provides 2 endpoints covering core functionality including reverse geocoding, search for addresses.
Call POST /reverse to reverse geocoding
Data Retrieval and Monitoring
Query PlaceKit API Reference endpoints to retrieve structured data for monitoring, reporting, or downstream processing. The API returns JSON responses that agents can parse directly, enabling automated data collection workflows without manual intervention.
Query the PlaceKit API Reference API to retrieve current data and verify the response contains expected fields
AI Agent Integration via Jentic
AI agents discover and call PlaceKit API Reference endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'reverse geocoding', load the operation schema, and execute with Jentic-managed credentials
2 endpoints — placekit openapi specifications ([repository](https://github.
METHOD
PATH
DESCRIPTION
/reverse
Reverse geocoding
/search
Search for addresses
/reverse
Reverse geocoding
/search
Search for addresses
What agents get from Jentic-routed access to this vendor.
Setup
Wiring PlaceKit by hand means learning its x-placekit-api-key header auth and building the request plumbing for its search and reverse geocoding calls yourself. Through Jentic you install once, import PlaceKit from the API Directory, store the API key once, and your agent calls it.
Permission scoping
PlaceKit exposes only geocoding operations that take their query in the request body (/search and /reverse), so scoping is operations-only: limit the agent to the operations it needs, such as forward search or reverse geocoding. You choose which of those operations it may call.
Credential isolation
Your PlaceKit API key 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 'search for a place' or 'reverse geocode a coordinate', and Jentic returns the matching PlaceKit 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.
Github
Alternative developer tools API
Choose Github when you need a different approach to developer tools operations
Specific to using PlaceKit API Reference API through Jentic.
What authentication does the PlaceKit API Reference use?
The PlaceKit API Reference uses an API key passed in the `x-placekit-api-key` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I reverse geocoding with the PlaceKit API Reference?
Yes. Use the POST /reverse endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the PlaceKit API Reference?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I reverse geocoding through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'reverse geocoding'. Jentic returns the matching PlaceKit API Reference operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the PlaceKit API Reference have?
The PlaceKit API Reference exposes 2 endpoints covering reverse, search operations.
Can I limit what my agent is allowed to do with the PlaceKit API?
Yes. Because you run Jentic One yourself, your own rules decide which PlaceKit operations the agent may call. PlaceKit exposes only two body-parameter geocoding operations, forward search (POST /search) and reverse geocoding (POST /reverse), so scoping is operations-only: you allow just the ones the agent needs and deny the rest. Your API key is held by your own instance and injected at execution time, so the agent never sees the raw credential.