For Agents
Programmatically create a new query, list all queries. Covers 10 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 Redash 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%2Fredash.io%2Fredash" | 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%2Fredash.io%2Fredash" | 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 Redash API.
Create a new query
List all queries
Update query
Get query by ID
GET STARTED
Use for: I need to a new query, I want to all queries, Search for query, Find all query by id
Not supported: Does not handle payments, communications, or crm - use for analytics only.
Redash is a data visualization and dashboarding platform. The API allows you to programmatically create queries, refresh data, manage dashboards, and access query results. The API exposes 10 endpoints secured with apiKey authentication.
Delete query
Refresh query results
Patterns agents use Redash API for, with concrete tasks.
★ Analytics Operations
Use the Redash API to perform analytics operations programmatically. The API provides 10 endpoints covering core functionality including create a new query, list all queries, update query.
Call POST /queries to create a new query
Automated Queries Management
Automate queries operations by combining multiple Redash API endpoints. Agents can list all queries and then update query in a single workflow.
Call GET /queries to list all queries, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Redash API 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 'create a new query', load the operation schema, and execute with Jentic-managed credentials
10 endpoints — redash is a data visualization and dashboarding platform.
METHOD
PATH
DESCRIPTION
/queries
Create a new query
/queries
List all queries
/queries/{query_id}
Update query
/queries/{query_id}
Get query by ID
/queries/{query_id}
Delete query
/queries/{query_id}/results
Refresh query results
/dashboards
List all dashboards
/dashboards/{dashboard_slug}
Get dashboard by slug
/queries
Create a new query
/queries
List all queries
/queries/{query_id}
Update query
/queries/{query_id}
Get query by ID
/queries/{query_id}
Delete query
/queries/{query_id}/results
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Redash API by hand means learning its apiKey auth and pointing every request at your own instance host (/{instance}.redash.io/api). Through Jentic you install once, import the Redash API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Redash puts the query id in the URL path (/queries/{query_id}), so a rule can pin your agent to specific queries. You choose the operations it may call, so writes like deleting a query or running its results are only included if you add them.
Credential isolation
Your Redash 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 'create a query' or 'fetch query results', and Jentic returns the matching Redash 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 Redash API through Jentic.
What authentication does the Redash API use?
The Redash API uses an API key passed in the `api_key` query. 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 create a new query with the Redash API?
Yes. Use the POST /queries endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Redash API?
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 create a new query through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create a new query'. Jentic returns the matching Redash API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Redash API have?
The Redash API exposes 10 endpoints covering queries, dashboards, data sources operations.
Can I limit what my agent is allowed to do with the Redash API?
Yes. Because you self-host Jentic One, your own rules decide which Redash operations and credentials the agent may use. Since Redash puts the query id in the URL path (/queries/{query_id}), you can pin the agent to specific queries and choose exactly which operations it calls, such as allowing GET /queries to list and read while withholding write actions. Destructive calls like DELETE /queries/{query_id} or POST /queries/{query_id}/results to refresh results are only available to the agent if you add them.
Refresh query results
/dashboards
List all dashboards
/dashboards/{dashboard_slug}
Get dashboard by slug