# Agent access policy, defined with a sourced example

GLOSSARY, read 13 Nov 2026

**The short answer.** A rule that sets what a given AI agent may read or do, kept apart from the policies written for people. It names the agent, the data it may reach and the actions it may take. OvalEdge's docs say that after OAuth 2.0 sign-in to its MCP server, role-based access, policies and audit logging still apply.

## Definition

A rule that sets what a given AI agent may read or do, kept apart from the policies written for people. It names the agent, the data it may reach and the actions it may take. Reviewers use it to approve an agent before it connects.

## Example from a real source

**Example.** OvalEdge's docs say that after OAuth 2.0 sign-in to its MCP server, role-based access, policies and audit logging still apply.

## Related terms

- [AI data governance](/glossary/ai-data-governance/): The rules and records that decide which data an AI system may read, what it may be told about that data, and who can prove it afterward.
- [attribute-based access control (ABAC)](/glossary/attribute-based-access-control/): A way to grant access by comparing attributes of the person, the data and the situation, rather than by listing who may open which table.
- [access review](/glossary/access-review/): A check, by a person or a rule, of whether an access request or an existing grant should stand.

## Where to read more

- [The PII Exposure Map](/exposure-map/)
- [All glossary terms](/glossary/)

## Sources

- docs.ovaledge.com/release8.3/mcp-server/whats-new.md: https://docs.ovaledge.com/release8.3/mcp-server/whats-new.md (read 13 Nov 2026)

Last reviewed 13 Nov 2026. Canonical: https://aidatagovernancetools.com/glossary/agent-access-policy/
