Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Data Network 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%2Fopendatanetwork.com%2Fopendatanetwork" | 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%2Fopendatanetwork.com%2Fopendatanetwork" | 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 Open Data Network API.
Search datasets across public open-data providers
Search the questions that datasets can answer
Retrieve values for a variable across entities
Check data availability for an entity
Explore relationships between entities such as parent and peer places
GET STARTED
Suggest entities, datasets, and questions by type
Patterns agents use Open Data Network API for, with concrete tasks.
★ Dataset Discovery
A research agent finds relevant public data by calling GET /search/v1/dataset with a topic, then follows up with GET /search/v1/question to learn what those datasets can answer. This replaces manual browsing of open-data portals.
Search datasets with GET /search/v1/dataset, then GET /search/v1/question for what they answer
Comparative Statistics
An analytics agent pulls a metric across places by calling GET /data/v1/values for a variable, giving a side-by-side view without a custom extract step. It is useful for building quick regional comparisons.
Retrieve the variable across entities with GET /data/v1/values
Availability Checks
Before promising an answer, an agent calls GET /data/v1/availability/ to confirm a place has data for the variable of interest. This avoids returning empty results to a user.
Confirm coverage with GET /data/v1/availability/ before querying values
Place Relationships
An agent navigates geographic hierarchy with GET /entity/v1/{relation} to find the parent state of a county or peer places. This lets it roll up or compare figures at the right level.
Walk the hierarchy with GET /entity/v1/{relation} to find parent or peer places
9 endpoints — the open data network api is a search and data layer over public datasets published by governments and other open-data providers.
METHOD
PATH
DESCRIPTION
/search/v1/dataset
Search datasets
/search/v1/question
Search questions datasets can answer
/data/v1/values
Retrieve values for a variable
/data/v1/availability/
Check data availability for an entity
/entity/v1/{relation}
Explore relationships between entities
/search/v1/dataset
Search datasets
/search/v1/question
Search questions datasets can answer
/data/v1/values
Retrieve values for a variable
/data/v1/availability/
Check data availability for an entity
/entity/v1/{relation}
Explore relationships between entities
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Open Data Network API by hand means learning its 9 operations across search, data, and entities, and handling pagination and query parameters against http://api.opendatanetwork.com. Through Jentic you install once, import the Open Data Network API from the API Directory, and your agent calls it.
Permission scoping
Because you run Jentic One yourself, you decide which Open Data Network operations the agent may call. Every operation is a read, so you can expose only the search endpoints, or only the data endpoints, and leave the rest out of the allowed set unless you add them.
Credential isolation
The Open Data Network API declares no authentication, so there is nothing to hold or inject. Jentic calls its public read-only endpoints directly, and no secret ever enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent, such as 'search for datasets about housing' or 'compare a variable across states', and Jentic returns the matching Open Data Network operation with its input schema so the agent calls the right endpoint.
Alternatives and complements available in the Jentic catalogue.
Specific to using Open Data Network API through Jentic.
What can an AI agent do with the Open Data Network API?
An agent can search public datasets and the questions they answer, retrieve values for a variable across places, check data availability, and explore relationships between entities such as a county and its parent state. It is a read-only layer over open public data.
Does the Open Data Network API require authentication?
The specification declares no authentication scheme, so the endpoints are public and read-only. There is nothing to sign in with, and through Jentic your agent calls the endpoints directly.
How do I find the right dataset through the API?
Call GET /search/v1/dataset with a topic to list matching datasets, then GET /search/v1/question to see what those datasets can answer. Pairing the two lets an agent move from a broad topic to a specific query.
Is there an MCP server for the Open Data Network API?
You do not need a separate MCP server to use the Open Data Network API with an agent. Through Jentic One, the self-hosted execution layer, your agent calls the operations directly after you import them from the API Directory. Install Jentic One from github.com/jentic/jentic-one to run it yourself.
How does my agent discover Open Data Network operations through Jentic?
Agents search Jentic by intent, such as 'search for datasets about housing', and Jentic returns the matching operation with its input schema. The agent then calls the right endpoint without reading the full reference.
Can I limit what my agent is allowed to do with the Open Data Network API?
Yes. Because you run Jentic One yourself, you decide which Open Data Network operations the agent may call. Since every operation is a read, you can also expose only search or only the data endpoints, so the agent acts only within the operations you permit.
Know of an official OpenAPI document? Contribute it →
For Agents
Search public datasets, retrieve variable values, and explore entity relationships across the Open Data Network.
Use for: Search for datasets about a topic, Find which questions a dataset can answer, Retrieve values for a variable across places, Check whether data is available for a place
Not supported: Does not host or publish datasets itself. Use it to search public datasets and questions, retrieve variable values and availability, and explore entity relationships across the Open Data Network.
The Open Data Network API is a search and data layer over public datasets published by governments and other open-data providers. An agent can search for datasets and for the questions they answer, retrieve values for a variable, check which entities have data available, and walk relationships between places such as a county and its parent state. It suits research and analytics work that needs public statistics without standing up a data pipeline. The API is read-only and needs no credentials.