Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Dune Analytics 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%2Fdune.com%2Fdune" | 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%2Fdune.com%2Fdune" | 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 Dune Analytics API.
Execute saved queries or raw SQL against on-chain data across multiple blockchains
Retrieve query execution results as JSON or CSV once an execution completes
Poll execution status and cancel a running execution
Create, update, archive, and toggle the privacy of saved queries
Upload custom datasets by creating tables and inserting or replacing rows from a CSV
GET STARTED
Check API credit usage for your team
Patterns agents use Dune Analytics API for, with concrete tasks.
★ AI Agent On-Chain Analytics
Let an AI agent answer blockchain data questions on demand: it executes a saved Dune query, polls the execution status until it completes, and retrieves the results as JSON for the agent to summarize. Through Jentic the agent discovers the right Dune operation by intent and calls it with the query id, so an analytics loop runs without a developer wiring the execute-poll-fetch sequence by hand.
Execute saved query 123456, poll its execution status until complete, then retrieve the results as JSON
SQL Blockchain Data Queries
Analysts and agents run ad-hoc SQL directly against Dune's indexed on-chain datasets instead of maintaining their own node. The raw SQL execute operation returns an execution id, which you poll for status and then fetch results from as JSON or CSV. This supports one-off investigations and scheduled reporting over multiple chains.
Submit a raw SQL query that aggregates daily transaction counts for a contract, then fetch the execution results as CSV
Custom Dataset Uploads
Teams enrich on-chain analysis with their own off-chain data by uploading it to Dune as tables. The API creates a table in your namespace, inserts rows or replaces the whole table from a CSV upload, and clears the data before the next load. Uploaded tables can then be joined in SQL queries alongside on-chain datasets.
Create a table in your namespace, upload a CSV to populate it, then clear the data before the next load
Saved Query Management
Dashboards and recurring reports are backed by saved queries that need version control. The API creates a saved query, reads and updates its SQL, archives or unarchives it, and toggles whether it is private or public. Agents use this to maintain a library of queries without opening the Dune web editor.
Create a saved query, update its SQL, then make the query private
21 endpoints — the dune analytics api runs sql-based analytics queries over on-chain data across multiple blockchains and returns the results programmatically.
METHOD
PATH
DESCRIPTION
/v1/sql/execute
Execute raw SQL
/v1/query/{query_id}/execute
Execute a saved query
/v1/execution/{execution_id}/results
Get execution results
/v1/execution/{execution_id}/status
Get execution status
/v1/query
Create a new saved query
/v1/table/create
Create an uploaded table
/v1/table/upload/csv
Upload CSV to create or replace a table
/v1/billing/usage
Get API usage
/v1/sql/execute
Execute raw SQL
/v1/query/{query_id}/execute
Execute a saved query
/v1/execution/{execution_id}/results
Get execution results
/v1/execution/{execution_id}/status
Get execution status
/v1/query
Create a new saved query
/v1/table/create
Create an uploaded table
/v1/table/upload/csv
Upload CSV to create or replace a table
/v1/billing/usage
Get API usage
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Dune by hand means managing its X-Dune-Api-Key header, the execute-then-poll-then-fetch result flow, and CSV versus JSON result handling yourself. Through Jentic you install once, import Dune from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Dune carries the query id and table namespace in the URL path (/v1/query/{query_id}, /v1/table/{namespace}/{table_name}), so a rule can scope your agent to specific queries or tables and the operations you pick. You choose the operations it may call, so running queries and reading results can be allowed while deleting a table or clearing its data are not included unless you add them.
Credential isolation
Your Dune 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 'execute an on-chain query' or 'upload a dataset', and Jentic returns the matching Dune 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 Dune Analytics API through Jentic.
What authentication does the Dune Analytics API use?
The Dune Analytics API authenticates with an API key sent in the X-Dune-Api-Key header per its OpenAPI spec. Keys are auto-generated for new teams and managed in account settings. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.
Can I run raw SQL with the Dune Analytics API?
Yes. The SQL execute operation submits a raw SQL statement against Dune's on-chain datasets and returns an execution id, which you poll for status and then fetch results from as JSON or CSV. Saved queries work the same way through the saved-query execute operation.
What are the rate limits for the Dune Analytics API?
The OpenAPI spec does not specify rate limits; see https://docs.dune.com/api-reference for current plan limits. You can track consumption with the billing usage operation, which returns your team's current API usage so an agent can stay within its credit allowance.
Is there a Dune Analytics MCP server?
You don't need an MCP server to give your agent the Dune Analytics API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls operations like executing a query or uploading a dataset. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the Dune Analytics API?
Yes. Write a rule that allows only query execution and result retrieval, so the agent can run SQL and read results but cannot delete a table or clear its data. Because Dune addresses queries and tables by id in the URL path, a rule can also pin the agent to specific queries or tables, and every call it makes is logged.
How do I execute an on-chain query with the Dune Analytics API through Jentic?
Search Jentic for 'execute an on-chain analytics query' to find the execute operation, run your saved query or raw SQL, then poll the execution status and fetch the results. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Execute SQL and saved queries against on-chain data, retrieve results as JSON or CSV, and upload custom datasets. Covers 21 operations across executions, queries, and tables.
Use for: Execute a saved Dune query and fetch the results, Run raw SQL against on-chain data, Check the status of a query execution, Retrieve query results as CSV
Not supported: Does not handle on-chain transaction execution, wallet management, or token transfers. Use for on-chain analytics queries and dataset management only.
The Dune Analytics API runs SQL-based analytics queries over on-chain data across multiple blockchains and returns the results programmatically. Agents can execute a saved query or raw SQL, poll the execution status, and retrieve results as JSON or CSV, as well as create, update, archive, and change the visibility of saved queries. Custom datasets can be uploaded by creating tables and inserting rows or replacing them from a CSV. Authentication uses a Dune API key sent in the X-Dune-Api-Key header.
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>