incident_response
Incident response: volatile data, IOC scan, timeline, forensics (memory/disk/network/evidence/custody)
This record as markdown: /tools/defense/incident-response.md
What incident_response does on Defense
AI agents invoke incident_response to trigger actions in Defense. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
path | string | — | Root path to search |
hours | number | — | Hours to look back for modifications |
action | string | Yes | Incident response action |
device | string | — | Device path, e.g. /dev/sda1 |
case_id | string | — | Case identifier for custody tracking |
dry_run | boolean | — | Preview without executing |
duration | number | — | Capture duration in seconds (max 300) |
examiner | string | — | Name of the forensic examiner |
interface | string | — | Network interface for capture |
check_type | string | — | IOC check type |
file_types | string | — | File types to include |
output_dir | string | — | Output directory for artifacts |
Parameters from the server's own tool schema.
Why incident_response is rated High
Incident response tooling that performs IOC scanning, memory/disk/network forensics, and evidence collection actively reads from and interacts with live system state (volatile data), runs scans and analysis processes across memory, disk, and network, and manages evidence chains of custody. These are active execution operations with wide system access.
From the tool's definition volatile data, IOC scan, timeline, forensics (memory/disk/network/evidence/custody)
Risk signalsAccepts file system path (path) · High parameter count (16 properties)
Attacks that exploit this kind of access
The rule that runs incident_response safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For incident_response, this is the rule to start with:
incident_response stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every incident_response call is checked against it from then on.
Questions about incident_response
Incident response: volatile data, IOC scan, timeline, forensics (memory/disk/network/evidence/custody). It is categorised as a Execute tool in the Defense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
incident_response accepts 12 parameters: path, hours, action, device, case_id, dry_run, duration, examiner, interface, check_type, file_types, output_dir. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Defense MCP server in PolicyLayer and add a rule for incident_response: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.
incident_response is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the incident_response rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for incident_response. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
incident_response is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defense, and thousands of servers like it.
Across the catalogue