The safeguards map / 3.6 Identity and authorization
Jentic One
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An open-source broker that agents call instead of holding API keys; it checks the agent's permissions, injects the stored credential and records each execution.
Where it sits
3.6 Identity and authorization (primary): Sits between an agent and the APIs it calls, checks the agent's permissions on each call and attaches the stored credential so the agent never holds it.
The Broker checks the agent's permissions, attaches the credential at execution time, and writes an execution record.
captured
Register the APIs an agent may use, store the credentials once, and the agent makes its calls through the Broker.
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agentAI system
- Used by
- those who run it
- Runs
- at runtime
- Policy comes from
- owner-entered settings
Handoffs
None recorded.
Listed, not drawn: no documented handoff and no foundation home places it on the map.
Collector's note
Placed in 3.6 because the docs describe a permission check and credential brokering for API calls, not model, Model Context Protocol (MCP) or agent-to-agent traffic. It exposes a local MCP server as one client path; the broker is the enforcement point.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.