abnormal-mcp
abnormal-mcp is an MCP server for Abnormal Security that enables AI-powered email threat detection, investigation, case management, and remediation.
Navigate & Discover: Use
abnormal_navigateto explore available tools by domain (threats, messages, remediation, abuse, cases) andabnormal_statusto check connection status.Threat Management: List paginated detected threat cases (
abnormal_threats_list) and retrieve full details of a specific threat by ID (abnormal_threats_get), including classification, severity, and related messages — rendered as an interactive card in compatible MCP Apps hosts (e.g., Claude Desktop/web).Message Analysis: List all messages within a threat case (
abnormal_messages_list) and get deep analysis of individual emails (abnormal_messages_get), including headers, URLs, attachments, and AI-based threat assessment.Remediation: Trigger email remediation to remove a malicious message from mailboxes, restore it (unremediate), or check the current remediation status (
abnormal_remediation_manage).Abuse Mailbox: List and review phishing emails reported by users (
abnormal_abuse_list), including whether Abnormal confirmed the threat.Security Cases: List active security investigation cases (
abnormal_cases_list) and retrieve detailed information about a specific case (abnormal_cases_get), including status, analyst notes, associated threats, and timeline.
abnormal-mcp
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
Tool | Description |
| Navigate to a domain (threats, messages, remediation, abuse, cases) |
| Return to domain selection |
Threats domain
Tool | Description |
| List detected threat cases (paginated) |
| Get full details of a specific threat by ID |
Messages domain
Tool | Description |
| List messages within a threat case |
| Get detailed message analysis (headers, URLs, attachments, AI analysis) |
Remediation domain
Tool | Description |
| Trigger or check remediation actions for a message |
Abuse domain
Tool | Description |
| List phishing emails reported via the Abuse Mailbox |
Cases domain
Tool | Description |
| List active security investigation cases |
| Get details of a specific case |
Interactive Threat Card (MCP Apps)
abnormal_threats_getrenders 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 viawindow.__BRAND__injection orMCP_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.
Related MCP server: blumira-mcp
Authentication
Abnormal Security uses Bearer token authentication. Copy .env.example and set the variables below.
Variable | Required | Description |
| For stdio and | Abnormal Security API token. Generate it in the Abnormal portal under Settings > Integrations > API. |
| No |
|
| No |
|
| Yes for HTTP | Service-to-service secret. Generate one with |
| No | Set to exactly |
| No | Bind address when |
| No | HTTP port. Defaults to |
/health stays unauthenticated and does not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.
X-Gateway-S2S signing
With MCP_TRANSPORT=http and a real CONDUIT_S2S_SECRET, every /mcp request must include X-Gateway-S2S. The header value is t=<unix seconds>,v1=<hex>, where the hex is HMAC-SHA256 of the literal string t=<unix seconds> keyed with CONDUIT_S2S_SECRET (64 lowercase hex characters). The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns 401 before the Abnormal token is read.
TS=$(date +%s)
SIG=$(printf 't=%s' "$TS" | openssl dgst -sha256 -hmac "$CONDUIT_S2S_SECRET" -hex | awk '{print $NF}')
curl -sS http://127.0.0.1:8080/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H "X-Gateway-S2S: t=${TS},v1=${SIG}" \
-H "Authorization: Bearer $ABNORMAL_API_TOKEN" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'In AUTH_MODE=gateway that Authorization header is required and is the only credential source. AUTH_MODE=env still requires a valid X-Gateway-S2S header, then uses ABNORMAL_API_TOKEN from the environment when the request does not carry Authorization.
Standalone (env mode)
export ABNORMAL_API_TOKEN=your-api-token
node dist/index.jsGateway mode
When deployed behind the MCP gateway, set AUTH_MODE=gateway. The gateway signs each /mcp request with X-Gateway-S2S and injects Authorization: Bearer {token}. Requests missing that credential header are rejected with 401.
Running
stdio (for Claude Desktop)
npm install
npm run build
node dist/index.jsHTTP Streamable (for hosted/gateway deployment)
HTTP refuses to start until CONDUIT_S2S_SECRET is a real secret:
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" MCP_TRANSPORT=http AUTH_MODE=gateway node dist/index.jsLocal HTTP without a secret is development-only. It binds 127.0.0.1 only and logs a warning:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:httpDocker
The image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the S2S secret. In gateway mode the API token arrives on each request as Authorization; the image does not read ABNORMAL_API_TOKEN.
docker build -t abnormal-mcp .
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-p 127.0.0.1:8080:8080 \
abnormal-mcpCompose refuses to start when CONDUIT_S2S_SECRET is unset, sets AUTH_MODE=gateway, does not inject ABNORMAL_API_TOKEN, and publishes 127.0.0.1:8080:8080:
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose upSingle-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses ABNORMAL_API_TOKEN:
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTH_MODE=env \
-e ABNORMAL_API_TOKEN=your-api-token \
-p 127.0.0.1:8080:8080 \
abnormal-mcpDevelopment
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
Available Tools
10 toolsabnormal_abuse_listA
List phishing emails reported by users via the Abuse Mailbox. Returns user-submitted reports with analysis results indicating whether Abnormal confirmed the threat.
Inputs: filter, pageSize, pageNumber.
abnormal_cases_getA
Get detailed information about a specific security case by ID. Returns case status, analyst notes, associated threats, and timeline.
Inputs: caseId (required).
abnormal_cases_listB
List all active security investigation cases in Abnormal Security. Cases group related threats for analyst review and workflow management.
Inputs: filter, pageSize, pageNumber.
abnormal_messages_getA
Get detailed analysis of a specific message within a threat case. Returns full message metadata, headers, URLs, attachments, and AI-based threat analysis.
Inputs: threatId (required), messageId (required).
abnormal_messages_listB
List messages contained within a specific threat case. Returns message IDs and summary data for all emails associated with the threat.
Inputs: threatId (required).
abnormal_remediation_manageA
Trigger or check the status of a remediation action for a specific threat message. Supports requesting remediation (removal from mailboxes) or checking current remediation status.
Inputs: action (required), threatId (required), messageId (required).
abnormal_statusC
Show connection status and available domains
Inputs: no named parameters.
abnormal_threats_getA
Get detailed information about a specific threat case by ID. Returns threat details including classification, severity, and related message IDs.
Inputs: threatId (required).
abnormal_threats_listB
List detected threats and cases from Abnormal Security. Returns a paginated list of threat IDs with summary information.
Inputs: filter, pageSize, pageNumber.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool targets a distinct resource-action pair, but cases and threats can be slightly confused since both have get-by-ID tools. The descriptions clarify that cases group related threats, so agents should mostly select correctly, though the boundary could be clearer.
The pattern abnormal_<resource>_<verb> is mostly consistent (list/get for cases, threats, messages), but abnormal_navigate and abnormal_status break the pattern, and remediation_manage uses a vaguer verb. Overall, the convention is clear and predictable with only minor exceptions.
10 tools is well within the sweet spot for a security-focused MCP server. The count covers the major domains (cases, threats, messages, remediation, abuse reporting) without unnecessary bloat.
The core read-heavy workflows are well covered: list/get cases, threats, messages, plus remediation and abuse reports. Notable gaps include the lack of an update-case or update-threat operation, and abuse reports only support listing without a get-detail tool, but these are minor for a typical analyst workflow.
Maintenance
Related MCP Connectors
Cybersecurity MCP server for URL scanning, threat intelligence, and domain reputation.
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Remote MCP server bridging AI clients with the PowerDMARC email authentication Platform.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that integrates ThreatBook's threat intelligence API, offering 15 specialized tools for security analysis. It enables AI models to perform IP reputation checks, domain investigations, file sandbox analysis, and vulnerability intelligence lookups.50MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server for Blumira SIEM platform, enabling management of security event detection, alerts, and threat response through Blumira's API.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceAn MCP server for Blackpoint Cyber MDR platform, enabling management of security monitoring, threat detection, and incident response through Blackpoint's API.Apache 2.0
- AlicenseAqualityBmaintenanceMCP server for Checkpoint Harmony Email & Collaboration (Avanan). Enables AI assistants to manage email security, anti-phishing, anti-malware, and threat detection via the Avanan API.131Apache 2.0