Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sanity Projects 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%2Fsanity.io%2Fsanity-projects-api" | 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%2Fsanity.io%2Fsanity-projects-api" | 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 Sanity Projects API.
Create a Sanity project with a displayName, optionally inside an existing organizationId
Create a dataset with a public, private, or custom aclMode, or update and delete it
Copy a dataset to a targetDataset, optionally with skipHistory for a faster copy, and list past copy jobs by state
Add a CORS origin with allowCredentials, or remove one, so a browser app can call the project
GET STARTED
Create a project token with a label and a roleName such as viewer or editor, and list or delete tokens
Create project tags and assign them to datasets to group environments
Read and update a dataset's embeddings index settings
Patterns agents use Sanity Projects API for, with concrete tasks.
★ AI agent provisioning environments
An agent setting up a test environment needs a fresh dataset and a way for the app to reach it. Through Jentic it searches for 'create a Sanity dataset', loads the dataset create operation, and creates a private dataset in the project, then adds the app's CORS origin, while the Sanity token is injected at call time. Each step is a separate operation, so the rule can allow provisioning without allowing deletion.
PUT /projects/{projectId}/datasets/{name} for dataset 'qa' with aclMode 'private', then POST /projects/{projectId}/cors with origin 'https://qa.example.com' and allowCredentials true
Cloning production for testing
Testing migrations safely means working on a copy of real content. The copy operation clones a dataset into a new targetDataset, with skipHistory to speed it up and skipContentReleases to leave release documents behind; it requires Sanity's Advanced Dataset Management feature on the Enterprise plan. Past copies, including their state, are listed from the copy jobs history.
PUT /projects/{projectId}/datasets/{name}/copy for dataset 'production' with targetDataset 'migration-test' and skipHistory true, then GET /projects/{projectId}/datasets/copy to confirm the job
Token and access housekeeping
Old tokens and stray CORS origins accumulate. The API lists every project token and CORS entry, deletes the ones no longer needed, creates new tokens with a unique label and roleName, and reports the caller's own permissions on the project so an audit can confirm who can do what.
Call GET /projects/{projectId}/tokens and GET /projects/{projectId}/cors, and report any token whose label mentions 'old' along with every origin allowed
30 endpoints — the sanity projects api administers sanity projects and the datasets inside them.
METHOD
PATH
DESCRIPTION
/projects
List all projects
/projects
Create a project
/projects/{projectId}/datasets
List a project's datasets
/projects/{projectId}/datasets/{name}
Create a dataset
/projects/{projectId}/datasets/{name}/copy
Copy a dataset
/projects/{projectId}/cors
Create a CORS entry
/projects/{projectId}/tokens
Create a project token
/projects/{projectId}/permissions
List your permissions for the project
/projects
List all projects
/projects
Create a project
/projects/{projectId}/datasets
List a project's datasets
/projects/{projectId}/datasets/{name}
Create a dataset
/projects/{projectId}/datasets/{name}/copy
Copy a dataset
/projects/{projectId}/cors
Create a CORS entry
/projects/{projectId}/tokens
Create a project token
/projects/{projectId}/permissions
List your permissions for the project
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Sanity Projects API by hand means templating the apiVersion into the host, sending a bearer token with project-level permissions, and knowing which dataset features each plan allows. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls it.
Permission scoping
Sanity puts the project id and dataset name in the URL path (/projects/{projectId}/datasets/{name}), so a rule can pin your agent to one project or one dataset. You choose the operations it may call, so destructive ones like deleting a project or dataset, or creating tokens, are not included unless you add them.
Credential isolation
Your Sanity token 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 Sanity dataset' or 'add a CORS origin to a Sanity project', and Jentic returns the matching Projects API operation with its input schema.
Alternatives and complements available in the Jentic catalogue.
Specific to using Sanity Projects API through Jentic.
What authentication does the Sanity Projects API use?
Per its OpenAPI spec, the Sanity Projects API uses a bearer token in the Authorization header. What a token can do depends on its permissions, which GET /projects/{projectId}/permissions lists for the caller. Through Jentic the token is stored by your own instance and attached at call time, so it stays out of the agent's context.
Can I copy a Sanity dataset with the Projects API?
Yes, with PUT /projects/{projectId}/datasets/{name}/copy and a targetDataset name. The spec says this is part of Advanced Dataset Management on the Enterprise plan; without it the request fails. Set skipHistory to true for a faster copy that leaves revision history behind.
Where do I manage Sanity roles and permissions?
The spec points role and permission management to Sanity's separate Access API. The Projects API reads your own permissions for a project and assigns a roleName or roleNames when creating a token, and on a Free plan roleName must be viewer, editor, or deploy-studio.
What are the rate limits for the Sanity Projects API?
The OpenAPI spec does not specify rate limits. Check the Sanity documentation at https://www.sanity.io/docs for current API limits for your plan.
Is there a Sanity MCP server?
You don't need an MCP server to give your agent the Sanity Projects API. Jentic connects it directly from the API Directory: import it, store your Sanity token once, and your agent discovers the project, dataset, CORS, and token operations on demand.
How do I create a Sanity dataset through Jentic?
Search Jentic for 'create a Sanity dataset', load the createDataset operation, and execute PUT /projects/{projectId}/datasets/{name} with an aclMode of public or private. Private datasets need the private datasets feature on the project. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Sanity Projects API?
Yes. Write a rule that allows GET /projects/abc123/datasets and PUT /projects/abc123/datasets/{name} only, and the agent can list and create datasets in that one project but cannot delete datasets, change CORS, or mint tokens. Every call it makes is logged.
For Agents
Create and configure Sanity projects and datasets, copy datasets, manage CORS origins, project tokens, and dataset tags, and read a project's features and your permissions.
Use for: Create a staging dataset in my Sanity project, List all datasets in project abc123 with their stats, I need to allow https://www.example.com as a CORS origin, Copy production into a new dataset called qa without history
Not supported: Does not read or write documents, run GROQ queries, or manage custom roles. Use for administering Sanity projects, datasets, CORS origins, tokens, and tags only.
The Sanity Projects API administers Sanity projects and the datasets inside them. It lists, creates, updates, and deletes projects, and within a project creates datasets with a public, private, or custom ACL mode, updates or deletes them, copies one dataset into a new one, and lists the history of copy jobs. Projects also carry CORS origins, API tokens with assigned roles, tags that can be assigned to datasets, per-dataset embeddings index settings, active features, and the caller's own permissions. Role and permission management lives in Sanity's separate Access API.
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>