Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sanity Activity Log 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-activity-log" | 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-activity-log" | 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 Activity Log API.
Retrieve recent Sanity activity events in reverse chronological order with getActivityLogEvents
Filter events by actorId, userId, projectId, organizationId, or one or more action names
Bound an audit query to a time window with startTime and endTime
Page through matching events with limit and offset, capped at 100 events per JSON page
GET STARTED
Export matching activity events as a CSV file with exportActivityLogEventsCsv, up to 50000 rows per export
Patterns agents use Sanity Activity Log API for, with concrete tasks.
★ AI agent audit assistant
A developer asks their agent who changed something in a Sanity organization. Through Jentic the agent searches for 'get Sanity activity log events', loads the getActivityLogEvents operation with its filter parameters, and calls it with the right actorId, projectId, or action values while the Sanity token is injected at call time. The answer comes straight from the audit trail rather than from guesswork.
Call GET /v2021-02-01/activity with organizationId set to the team's organization, action=organization.name.edit, and a startTime seven days ago, then summarise who made each change
Compliance evidence export
Security reviews often ask for a record of who did what in the content platform. The Activity Log API exports matching events as a CSV with alphabetically sorted headers and metadata keys as their own columns, defaulting to 10000 rows and capped at 50000, so a reviewer gets a spreadsheet-ready file for a set time window.
Call GET /v2021-02-01/activity/export/csv with projectId for the production project, startTime 2026-10-01T00:00:00Z, endTime 2026-10-31T23:59:59Z, and limit 50000, and save the returned file
Per-user activity review
When someone leaves a team, it helps to see what they touched. Filtering activity events by actorId shows the actions that user performed, and filtering by userId shows events that targeted them, such as membership changes, each with timestamps, project, and dataset context.
Call GET /v2021-02-01/activity with actorId set to the departing user's ID and limit 100, then page with offset until no more events return
2 endpoints — the sanity activity log api returns the audit trail of activity events across sanity organizations, projects, and users, newest first by timestamp.
METHOD
PATH
DESCRIPTION
/v2021-02-01/activity
Get activity log events as JSON
/v2021-02-01/activity/export/csv
Export activity log events as CSV
/v2021-02-01/activity
Get activity log events as JSON
/v2021-02-01/activity/export/csv
Export activity log events as CSV
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Sanity Activity Log API by hand means sending a bearer token, encoding repeatable array query parameters like action and projectId, and handling 401s when a filter names a project the token cannot see. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls it.
Permission scoping
Both operations are reads and the project and organization filters travel as query parameters, not in the URL path, so a rule bounds which of the two operations your agent may call rather than which project it reads. The token's own access decides which events come back.
Credential isolation
Your Sanity API 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 'get Sanity activity log events' or 'export Sanity audit log', and Jentic returns the matching operation with its filter parameters so the agent builds the query without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Sanity Activity Log API through Jentic.
What authentication does the Sanity Activity Log API use?
Per its OpenAPI spec, the Sanity Activity Log API uses a bearer token: a Sanity API token sent as Authorization: Bearer followed by the token. Results only include activity the token's user can access, and filtering by a project or organization the token cannot access returns 401. Through Jentic the token is stored by your own instance and attached at call time.
Can I filter Sanity activity events by project or organization?
Yes. Both operations accept projectId and organizationId query parameters, and each can be repeated. On its own, organizationId matches only organization-level events, so filter by projectId to see activity inside a project, or omit both to get all activity the token can access.
How many events can I get from one Sanity Activity Log request?
The JSON endpoint returns 10 events by default and caps limit at 100, with offset for paging. The CSV export defaults to 10000 events and caps limit at 50000.
What are the rate limits for the Sanity Activity Log 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 Activity Log MCP server?
You don't need an MCP server to give your agent the Sanity Activity Log API. Jentic connects it directly from the API Directory: import it, store your Sanity token once, and your agent discovers the activity operations on demand instead of loading a server's tool list into its context.
How do I find out who changed something in Sanity through Jentic?
Search Jentic for 'get Sanity activity log events', load the getActivityLogEvents operation, and execute GET /v2021-02-01/activity with filters such as action, projectId, and startTime. 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 Activity Log API?
Yes. Write a rule that allows the JSON events read but not the CSV export, and the agent can answer audit questions in small pages while bulk exports stay with you. Every call it makes is logged.
For Agents
Read and export Sanity activity events filtered by actor, user, project, organization, action, and time window, as JSON pages or a CSV file.
Use for: Who changed the organization name last week?, List all activity in the marketing project since Monday, Find all events performed by a specific Sanity user, Export the last month of organization activity as a CSV
Not supported: Does not edit content, manage project members, or restore datasets. Use for reading and exporting Sanity activity events only.
The Sanity Activity Log API returns the audit trail of activity events across Sanity organizations, projects, and users, newest first by timestamp. Events can be filtered by actor, target user, project, organization, action name such as organization.name.edit, and a start and end time window. The same filters drive a CSV export, which sorts its headers alphabetically and spreads event metadata into dynamic metadata columns. Results only include activity that the token's user is allowed to see.
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>