Skip to main content
Glama
ZeroSOC

defender-xdr

by ZeroSOC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

defender_get_incident_evidence

Read-only

Retrieve the full evidence inventory of a Defender incident, with each item joined to its device and citing alerts. Review processes, files, IPs, registry keys, and more in one table.

Instructions

The full evidence inventory of an incident: the portal's evidence view as one table. Pages through every alert and flattens the evidence into one row per evidence item, each joined to its device (by device ID, else through the alert) and listing the alerts that cite it. A row is the source's own unit: entityCount equals the portal's count of evidence items and is the number to reconcile; rowCount is the number of per-alert evidence rows. The source lists one process more than once when alerts describe it differently (no image file, another path, a different verdict): those rows share instance (device, PID, creation time), sameProcess groups them with their verdicts, and processInstanceCount is the number of real processes. Rows carry type, name, PID and parent PID, full command line and its decoded -EncodedCommand payload, creation times in UTC, SHA1/SHA256, path, user SID and UPN, device ID, IP, registry key and value, detailed roles, verdict and remediation status. Follows a merged incident to its master. These are the entities the alerts cite, not raw telemetry: processes the detection did not flag are not here.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNoMaximum number of entities to return (default 200, max 1000).
skipNoNumber of entries to skip (paging).
typesNoOnly these entity types, e.g. ['process', 'file']. Types: device, user, process, file, ip, url, registry_key, registry_value, mailbox, and any other evidence type the source reports. entityCount always covers the whole incident.
incident_idYesThe incident ID, as shown in the Defender portal and the Graph API.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes far beyond the annotations (which are already read-only and open-world) by disclosing page-through/flattening behavior, entityCount vs rowCount semantics, duplicate row handling via instance/sameProcess/processInstanceCount, merged-incident following, and the fact that it only includes flagged entities, not raw telemetry. This is rich behavioral context that a caller needs to interpret results correctly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a dense paragraph, but every sentence contributes substantive information — flattening, deduplication, field inventory, merged incidents, and exclusions. It is not redundant, though better visual structure (bullets or headings) could improve scannability for a tool with this much behavioral nuance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given this is a complex tool with no output schema, the description compensates well by explaining return semantics (entityCount, rowCount, processInstanceCount), the row unit, deduplication logic, and the difference from other incident data. It covers all the essential information an agent needs to call the tool and interpret its response, within the context of the provided annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage for all parameters (top, skip, types, incident_id), including defaults and descriptions. The tool description does not add parameter-specific semantics beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the full evidence inventory of an incident as the portal's evidence view, with a specific verb/resource combination and detailed scoping. It distinguishes itself from sibling tools like defender_get_incident or defender_get_incident_alerts by focusing on flattened per-evidence rows with entities, not just alerts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on what the tool returns (evidence entities, not raw telemetry) and how it behaves with merged incidents, which implies when it is useful. However, it does not explicitly name alternatives or state when to prefer this over defender_get_incident_alerts or other sibling tools, so the guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools