AI & Agents

AI agents for endpoint security - on your terms

Most security platforms are adding AI as an afterthought - a chatbot layered over a legacy UI. LightEDR was designed from the ground up to be operated by AI agents. The MCP server, webhook system, and scoped service account model are not integrations. They are first-class features.

Request a demo →Product overview
Model Context Protocol

Connect any MCP-compatible AI in two config lines

The LightEDR MCP server (pip install ledr-mcp) exposes 13 named, described tools covering every major platform operation. Any MCP-compatible client - Claude, Cursor, Zed - connects with two environment variables and a JSON config block. No custom SDK. No proprietary protocol.

Available MCP tools

list_alertsQuery alerts by severity, technique, host, or time range
get_alertRetrieve full alert detail including raw event data
get_alert_contextSurrounding events, trust score, TI enrichment, similar past alerts
acknowledge_alertAcknowledge with a note - logged to audit trail
investigate_alertTrigger LLM-assisted triage analysis on demand
isolate_agentNetwork-quarantine an endpoint via the response API
unisolate_agentRestore network access to a previously isolated host
hunt_eventsNatural language event search across the entire fleet
get_mitre_coverageReturn the current MITRE ATT&CK coverage map
ledr-mcp · claude · active session
User

Are there any critical alerts in the last 4 hours? Investigate the highest-severity one and tell me if I should isolate the host.

Claude
→ list_alerts(severity=critical, since=4h)
→ get_alert_context(alert_id=A-48217)
→ investigate_alert(alert_id=A-48217)

Found 3 critical alerts. The highest-severity is T1003 credential dumping on web-01. Trust score is 0.42 - below the safe threshold. I recommend isolating the host. Want me to proceed?

Bring Your Own Agent

Model-agnostic by design

You are not buying a "Claude integration" or a "GPT feature." You are buying a security platform that any agent can operate. When better models ship, you upgrade the model. The security stack stays the same.

Scoped access

Principle of least privilege

Service account keys are scoped to exactly the permissions the agent needs - analyst read access for investigations, agents:manage only if host isolation is required. A compromised agent key cannot exceed its scope.

Full audit log

Every agent action is visible

The AI agent calls the same authenticated endpoints your analysts use. Every action is written to the tamper-evident, hash-chained audit log with actor, timestamp, and payload. No back-channel. No shadow operations.

Swap any time

No vendor lock-in on the model

The integration layer is the MCP server and the REST API - not the model. Switch from Claude to GPT to a local Ollama instance without changing a single line of your security configuration.

Webhook channels

Reactive, not polling

Autonomous agents that poll for alerts waste tokens and introduce latency. LightEDR calls your agent when a rule fires. The agent investigates and responds, then goes back to sleep.

  • Event-driven wake-up

    A detection rule matches. LightEDR POSTs the enriched alert payload to your registered webhook endpoint within milliseconds.

  • HMAC request verification

    Every webhook POST is signed with HMAC-SHA256. Your agent verifies the signature before processing - no spoofed alert payloads.

  • Exponential backoff retry

    If your endpoint is temporarily unavailable, LightEDR retries with exponential backoff. No alert is silently dropped.

  • Async-safe

    Webhook delivery is decoupled from detection. A slow or failing agent endpoint never delays alert processing or dashboard visibility.

webhook channel · channel-01 · active
Incoming - alert fired
alert_id: A-48217
severity: critical
technique: T1003.001
host: web-01
trust_score: 0.42
hmac_sig: sha256=7f3c...
Agent response - 340ms
action: isolate_agent
note: "Credential dump detected. Isolating pending investigation."
status: ✓ logged to audit trail
Compatible clients

Works with the tools you already use

The MCP server follows the open Model Context Protocol standard. If it speaks MCP, it works with LightEDR.

Claude

claude.ai · Claude Code

Set LEDR_URL and LEDR_KEY, add the MCP config block, and ask Claude about your alerts in plain English from the chat interface or directly from your terminal via Claude Code.

Cursor / Zed

AI-native editors

Both Cursor and Zed support MCP servers. Add the LightEDR server to your editor config and query your security posture without leaving your development environment.

Custom agents

REST API + webhooks

Build your own orchestration layer on the full REST API. Every UI action has an API equivalent. Webhook channels give you event-driven trigger capability. No MCP client required.

Get started

Connect your AI agent in under 10 minutes.

Request a sandbox tenant and we'll walk you through the MCP setup, webhook config, and your first agent-driven investigation. 14 days free, no credit card.

Request a demo →Full product overview