The safeguards map / 3.4 Guardrails
Cisco AI Defense
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
A commercial service that inspects prompts, responses and Model Context Protocol (MCP) messages for security and safety violations through an inspection API or a proxy gateway mode.
Where it sits
3.4 Guardrails (primary): Classifies chat and MCP JSON-RPC messages for security, privacy and safety violations through an inspection API that the calling application or gateway acts on.
Supports API mode (inspection) and Gateway mode (proxy).
captured
Inspect Model Context Protocol (MCP) JSON-RPC 2.0 messages for security, privacy, and safety violations in AI agent tool calls, resource access, and responses.
captured
3.3 Gateways: Offers a gateway mode that proxies model and MCP traffic, with MCP gateway policies managed through its API.
Supports API mode (inspection) and Gateway mode (proxy).
captured
MCPPolicyClient for managing MCP Gateway policies
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
- Traffic it sees
- model callstool calls (MCP)
- Can the agent bypass it
- depends
Handoffs
None recorded.
Listed, not drawn: no documented handoff and no foundation home places it on the map.
Collector's note
The product documentation host was not readable, so the placements rest on the vendor's product page and its SDK README. No MCP catalog was found in those pages. No handoff format is named there, so the entry is listed. The SDK is Apache-2.0; the service is proprietary.
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.