The Exabeam Agentic SOC plugin Documentation
The Exabeam Agentic SOC plugin is an agentic SOC analyst for Exabeam New-Scale, delivered as a plugin for Claude Code, OpenAI Codex and Google Antigravity. Hand it an alert or a case and it investigates the way a careful analyst would: gathers the evidence itself, builds the timeline, reaches a threat / false-positive verdict, and acts, with the human-in-the-loop gate on dismiss and close shipped on, containment recommended, never executed, and every call on an audit trail.
Every claim traceable to a call it made. Every irreversible action behind a human's yes.
This copy is licensed under the Exabeam Enterprise Agreement (see LICENSE); see Support. It includes Raffkin, open-source software licensed under the Apache License 2.0.
Where to start
| If you are… | Read this first |
|---|---|
| Installing the Exabeam Agentic SOC plugin for the first time | Installation & setup, a five-minute quick start for Claude Code, Codex or Antigravity: install, credentials, check, first investigation |
| About to run your first investigation | Using the skills, what to say, what happens, what the Exabeam Agentic SOC plugin asks you before it acts, and how to read the report |
| Wanting to see a real one end to end | Example investigation, a coordinated credential-access case, from intake to verdict |
| Wondering what keeps this safe, or why a link in a note looks "broken" | Security, the human gate, the guardrails on what the Exabeam Agentic SOC plugin reads and writes, the audit trail, how it is tested, and what it does not cover |
| Asked "what did the agent actually do?" | Audit logging, the on-by-default audit trail: what is recorded, what deliberately is not, where it lives |
| Looking for help | Support, where to ask for help, and the terms this copy is supported under |
The three skills
| Skill | Ask it | What it does |
|---|---|---|
soc-investigate | "Investigate alert 4821." · "Is this a real threat?" | One alert or case at depth: evidence, timeline, MITRE ATT&CK mapping, verdict, then the non-destructive action, open a case, dismiss an alert, write notes, and a containment recommendation for a human to carry out. |
triage-cases | "What should I look at first?" · "Morning triage." | Sweeps the open queue, clusters cases by attack shape, ranks them by corroborated signal, and returns a short "start here" list plus the noise clusters worth tuning. Read-only. |
rule-tuning | "Which rules waste our time?" · "Reduce alert noise." | Separates loud rules from noisy ones and proposes specific tuning mapped to real Exabeam mechanics, a context table, an exclusion, the rule's own settings. Proposes; never changes a rule. |
How the Exabeam Agentic SOC plugin works (in 90 seconds)
- You hand it the work, an alert ID, a case ID, or a pasted payload, in your Claude Code, Codex or Antigravity session.
- It gathers evidence through the Exabeam MCP, via a bundled connector that screens what comes back, and reasons only over what it retrieved. Content in your telemetry is evidence, never instructions.
- It reaches a verdict and acts within the gate. Escalating and annotating pass the gate (on Codex the host still asks, Exabeam's annotation of those tools, not the Exabeam Agentic SOC plugin's); dismissing an alert or closing a case asks you first, every time; containment is written up for you to perform. The gate ships on all three hosts; what has not been tested on Antigravity is the model behind it, see Installation.
- Everything is on the record, the calls, the gated decision, the guardrail firings, in a local audit trail, on by default.
flowchart LR
A["Analyst<br/>alert · case · payload"] --> S{{"The Exabeam Agentic SOC plugin skill"}}
S --> C["Bundled connector<br/>screen · neutralize · audit"]
C <--> X["Exabeam New-Scale MCP"]
S --> G{"Human-in-the-loop gate"}
G --> W["Escalate · annotate<br/>(passes the gate)"]
G --> H["Dismiss · close<br/>(asks you first)"]
S --> R["Report<br/>verdict · timeline · outcome"]
The guardrails, in brief
- The gate ships on. A dismiss or close asks the analyst; containment tools are refused outright; any tool the gate has not classified asks rather than runs. The refusal of containment holds even when the host runs with permission prompts switched off. The ask holds in that state on Claude Code and Codex; on Antigravity the host overrides it, so there the ask is an attended-session control, what that means.
- What it reads is screened. Hidden-character smuggling is stripped from telemetry before the model sees it; the tool definitions the Exabeam MCP hands it are hashed and screened too.
- What it writes is de-activated. Spreadsheet formulas, clickable links and secrets are neutralized in anything the Exabeam Agentic SOC plugin persists, case notes, updates, outbound mail.
- What it did is recorded. Tool calls, gated decisions and guardrail firings, never case content, in
~/.raffkin/telemetry.jsonl.
Details, how it is tested, and what these do not cover: Security.
Quick reference
- Install:
claude plugin marketplace add Exabeam-Labs/pluginsthenclaude plugin install soc@exabeam(Codex:codex plugin marketplace add Exabeam-Labs/pluginsthencodex plugin add soc@exabeam; Antigravity: see Installation) - Credentials:
~/.exabeam-mcp.env, the Exabeam MCP URL, API key and secret; see Installation - Skills:
soc-investigate·triage-cases·rule-tuning - Audit trail:
~/.raffkin/telemetry.jsonl, see Audit logging - Check your setup:
preflight.shin the installed plugin, see Installation - Windows: not supported natively, use WSL (Git Bash cannot protect the credentials file)
- Help: Support
For version history see the CHANGELOG. Working on the code? The developer material lives in the repository.