Abnormal

MCP server for Abnormal Security — AI-powered threat detection, case management, and email remediation.

Tools

This server uses a decision-tree architecture. Start by calling abnormal_navigate to select a domain, then use the domain-specific tools.

Navigation

Threats domain

Messages domain

Remediation domain

Abuse domain

Cases domain

Interactive Threat Card (MCP Apps)

• abnormal_threats_get renders as an interactive threat card in MCP Apps hosts (Claude Desktop/web): subject, sender, attack classification, remediation status, and the messages in the threat. The card is read-only — remediation stays a deliberate, model-mediated action. Plain-JSON behavior is unchanged in other hosts. Neutral by default, brandable via window.__BRAND__ injection or MCP_BRAND_* env vars (MCP_BRAND_NAME, MCP_BRAND_LOGO_URL, MCP_BRAND_PRIMARY_COLOR, MCP_BRAND_ACCENT_COLOR, MCP_BRAND_BG, MCP_BRAND_TEXT) — no rebuild needed.

Authentication

Abnormal Security uses Bearer token authentication.

Standalone (env mode)

export ABNORMAL_API_TOKEN=your-api-token
node dist/index.js

Generate your token in the Abnormal portal under Settings > Integrations > API.

Gateway mode

When deployed behind the MCP gateway, set AUTH_MODE=gateway. The gateway injects the Authorization: Bearer {token} header automatically on each request.

Running

stdio (for Claude Desktop)

npm install
npm run build
node dist/index.js

HTTP Streamable (for hosted/gateway deployment)

MCP_TRANSPORT=http AUTH_MODE=gateway node dist/index.js

Docker

docker compose up

Development

npm install
npm run dev          # watch mode
npm test             # run tests
npm run typecheck    # TypeScript type check
npm run build:ui     # rebuild the MCP Apps card bundle (only needed when ui/ changes)

License

Apache-2.0