Skip to main content

Security guardrails

Updated on 3 November 2026.

Scan what agents send to an MCP server and what the server sends back, and block, redact or flag sensitive data and attacks.

Request and response​

DirectionWhat is scanned
Request (tool arguments)The inputs sent when an agent calls a tool.
Response (tool results)What the tool returns before the AI client sees it.

Actions​

ActionWhat happens
BlockStops the tool call or withholds the result.
RedactRemoves detected data and lets the payload continue.
Partial redactMasks part of each match while retaining context.
MonitorLets the payload continue and records the detection.

Choose the instructions for the mode that governs your MCP Gateway. See Switching from classic settings for what happens to stored settings when the engine is on.

Going further with the Policy Engine​

Open Govern > Policy Engine > MCP Gateway > Controls > Data & Adversarial Risks. It has two sections:

SectionWhat it sets
Detection rulesSelected findings, the request/response stage and an action for a matching call or result.
Scan profileWhich detectors run, category-specific actions, and the fallback action.
  1. Choose a recipe or start a blank rule in the appropriate section.
  2. Choose Applies to, the data types or detectors, and the outcome.
  3. Check Reads as, then Save to draft.
  4. Use Test > Try a situation or Replay activity to check the candidate, then review and publish.

Detection rules resolve a payload-wide action: the highest numeric priority wins, with the stricter action winning ties. For each finding, that action competes by priority with the scan profile's category-specific or fallback action. Do not assume every Block overrides every higher-priority rule.

Scan-profile settings resolve per detector and per category. On wins a detector tie, and the stricter category action wins an action tie; the default action is a fallback. Detectors run only when a rule or profile selects them. Without selected checks, nothing is scanned automatically.

Rules that select detectors or set scan-profile actions run before scanning. Put conditions on Data found in a separate detection rule, rather than making the scan depend on a finding it has not yet produced.

Open Activity for observed matches. Classic settings marked Controlled by Policy Engine are stored for use when the engine is off; Edit anyway does not change published policies.

Where detections show​

  • Overall analytics > Data & security shows flagged request and response content in MCP Gateway Insights.
  • Findings & Interactions lists detections and supports input/output DLP filters.
  • The server card's Guardrails chip opens its configuration.