avanan-mcp
Connect an AI assistant to Check Point Avanan (Harmony Email & Collaboration) to investigate email security events, remediate threats, and manage exceptions.
Query security events (phishing, malware, DLP, anomaly, shadow IT, etc.) by type, state, severity, date, and SaaS platform, with pagination.
Retrieve detailed event information, including an interactive security event card in supported MCP Apps hosts.
Search and retrieve email/SaaS entities by sender, recipient, subject, platform, date range, and advanced attribute filters.
Quarantine or restore events and emails, then track task status via returned task IDs.
List, add, update, and delete whitelist/blacklist exceptions.
Works across SaaS platforms including email, Office 365, Slack, MS Teams, Google Mail/Drive, Box, and Dropbox.
Supports stdio and HTTP transports with S2S HMAC and gateway/env credential modes for MSP and multi-tenant use.
Avanan (Check Point) MCP Server
A Model Context Protocol (MCP) server for Check Point Avanan (Harmony Email & Collaboration). Enables AI assistants to manage security events, investigate threats, and handle multi-tenant MSP operations across your email security environment.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Check Point Avanan environment.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack. Built by MSPs, for MSPs.
Features
Interactive Security Event Card (MCP Apps):
hec_get_eventrenders as a read-only interactive card in MCP Apps hosts (Claude Desktop/web) showing severity, state, platform, and remediation status; neutral by default, brandable viawindow.__BRAND__injection orMCP_BRAND_*env vars; plain-JSON behavior is unchanged in other hosts
Related MCP server: mimecast-mcp
Installation
npm install @wyre-ai/avanan-mcpConfiguration
Copy .env.example and set the variables below. Leave CONDUIT_S2S_SECRET empty in that file.
Variable | Required | Description |
| For stdio and | Checkpoint/Avanan OAuth2 client ID |
| For stdio and | Checkpoint/Avanan OAuth2 client secret |
| No | API region ( |
| No |
|
| No |
|
| Yes for HTTP | Service-to-service HMAC secret. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder ( |
| No | Set to exactly |
| No | Bind address when |
| No | HTTP port. Defaults to |
/health stays unauthenticated. The stdio transport does not use CONDUIT_S2S_SECRET.
HTTP authentication
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 HTTP 401 before vendor credentials are 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 'X-Checkpoint-Client-Id: your-client-id' \
-H 'X-Checkpoint-Client-Secret: your-client-secret' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'In AUTH_MODE=gateway (the image and Compose default), /mcp also requires X-Checkpoint-Client-Id and X-Checkpoint-Client-Secret. Those headers are the only credential source for that request. A request missing either one returns 401 and does not fall back to CHECKPOINT_CLIENT_ID / CHECKPOINT_CLIENT_SECRET in the process environment.
Single-tenant HTTP (AUTH_MODE=env) still requires a valid X-Gateway-S2S header, then uses CHECKPOINT_CLIENT_ID and CHECKPOINT_CLIENT_SECRET when the request does not carry those headers.
Usage
Running with Claude Desktop
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"avanan-mcp": {
"command": "npx",
"args": ["@wyre-ai/avanan-mcp"],
"env": {
"CHECKPOINT_CLIENT_ID": "your-checkpoint-client-id"
"CHECKPOINT_CLIENT_SECRET": "your-checkpoint-client-secret"
}
}
}
}Running with Claude Code (CLI)
claude mcp add avanan-mcp \
-e CHECKPOINT_CLIENT_ID=your-value \
-e CHECKPOINT_CLIENT_SECRET=your-value \
-- npx -y @wyre-ai/avanan-mcpDocker
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 a real S2S secret. In gateway mode, Checkpoint credentials arrive on each request as headers; they are not read from the environment.
docker build -t avanan-mcp .
docker run \
-e CONDUIT_S2S_SECRET=your-s2s-secret \
-p 127.0.0.1:8080:8080 \
avanan-mcpCompose refuses to start when CONDUIT_S2S_SECRET is unset, sets AUTH_MODE=gateway, does not inject CHECKPOINT_CLIENT_ID or CHECKPOINT_CLIENT_SECRET, and publishes 127.0.0.1:8080:8080:
CONDUIT_S2S_SECRET=your-s2s-secret docker compose upSingle-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses CHECKPOINT_CLIENT_ID and CHECKPOINT_CLIENT_SECRET. Keep that off the gateway Compose service:
docker run \
-e CONDUIT_S2S_SECRET=your-s2s-secret \
-e AUTH_MODE=env \
-e CHECKPOINT_CLIENT_ID=your-value \
-e CHECKPOINT_CLIENT_SECRET=your-value \
-e CHECKPOINT_REGION=us \
-p 127.0.0.1:8080:8080 \
avanan-mcpLocal HTTP without a secret is development-only. It binds 127.0.0.1 even when MCP_HTTP_HOST is 0.0.0.0 or localhost, and logs a warning. A known placeholder secret still refuses to start:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm startAvailable Domains
Events
Security event retrieval and investigation
Actions
Take action on threats (quarantine, release, etc.)
Exceptions
Manage email exceptions and allowlists
Search
Search across email security data
Development
# Clone the repository
git clone https://github.com/WYRE-AI/avanan-mcp.git
cd avanan-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm testContributing
Contributions are welcome! Please see CONTRIBUTING.md if present, or open an issue to discuss changes.
License
Licensed under the Apache License, Version 2.0. See LICENSE for details.
Available Tools
13 toolshec_add_exceptionA
Add an entry to the whitelist or blacklist. At least one match field (senderEmail, senderDomain, subject, attachmentMd5, recipient) must be provided.
Inputs: excType (required), comment, subject, recipient, +7 more.
hec_delete_exceptionADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Delete a whitelist or blacklist entry by its entity ID. This action cannot be undone and will permanently remove the exception from security policy. Confirm with the user before invoking.
Inputs: excId (required), excType (required).
hec_get_emailA
Get full details for a specific email entity by its entity ID.
Inputs: entityId (required).
hec_get_eventB
Get full details for a specific security event by ID.
Inputs: eventId (required).
hec_get_task_statusA
Check the status of an action task (quarantine/restore). Use the taskId returned by quarantine or restore tools.
Inputs: taskId (required).
hec_list_exceptionsB
List whitelist or blacklist entries in Checkpoint Harmony Email.
Inputs: excType (required).
hec_quarantine_emailsADestructiveIdempotent
⚠ HIGH-IMPACT. Quarantine specific email entities by entity ID. Quarantining is reversible via restore but affects user access to emails. Returns task IDs to track progress. Confirm with the user before invoking.
Inputs: entityIds (required), entityType.
hec_quarantine_eventsADestructiveIdempotent
⚠ HIGH-IMPACT. Quarantine one or more security events by event ID. Quarantining is reversible via restore but affects user access to events. Returns task IDs to track progress. Confirm with the user before invoking.
Inputs: eventIds (required).
hec_query_eventsB
Query Checkpoint Harmony Email security events (phishing, malware, DLP, anomaly, shadow IT, etc.). Supports filtering by type, state, severity, date range, and SaaS platform. Returns events with available remediation actions.
Inputs: saas, endDate, eventIds, scrollId, +4 more.
hec_restore_emailsB
Restore specific quarantined email entities by entity ID.
Inputs: entityIds (required), entityType.
hec_restore_eventsA
Restore one or more previously quarantined events by event ID. Returns task IDs to track progress.
Inputs: eventIds (required).
hec_search_emailsB
Search email and SaaS entities in Checkpoint Harmony Email. Filter by sender, recipient, subject, SaaS platform, and date range. Use extended filters for precise attribute matching (contains, startsWith, isEmpty, etc.).
Inputs: saas (required), startDate (required), endDate, filters, +2 more.
hec_update_exceptionC
Update an existing whitelist or blacklist entry by its entity ID.
Inputs: excId (required), excType (required), comment, subject, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Most tools target a clearly distinct resource plus verb: exceptions (list/add/update/delete), events (query/get/quarantine/restore), emails (search/get/quarantine/restore), and task status. The main risk is the parallel quarantine/restore clusters for events vs emails, which overlap conceptually since email events and email entities are related, but the noun in each name disambiguates adequately.
Every tool uses the same hec_ prefix followed by a consistent verb_noun pattern (hec_list_exceptions, hec_query_events, hec_quarantine_emails, hec_get_task_status), with no mixed cases or style deviations.
13 tools is squarely in the well-scoped range, and each tool maps to a distinct operation across the domain's three resource families plus task tracking, with no filler.
Exceptions have full CRUD coverage, and events/emails both have read, quarantine, and restore, plus task status for async actions. Minor gaps remain: no explicit get-exception-by-id detail tool and no generic remediation beyond quarantine/restore, though these are workable through list and query.
Maintenance
Related MCP Connectors
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.
CheckFlow’s own MCP server. Ask your AI assistant to start checklists, complete tasks, fill in fields, build templates from written procedures and update Data Sets in CheckFlow. Sign in with your CheckFlow account, or use an API key.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseBqualityBmaintenanceMCP server for Proofpoint Email Protection - email security, threat intelligence, TAP (Targeted Attack Protection), and email filtering API integration406Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server for Mimecast Email Security — message tracking, threat intelligence, and email queue management. Enables AI assistants to investigate and manage email security events.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server for Spanning Cloud Backup — M365/GWS/Salesforce SaaS backup, restore, and audit. Enables AI assistants to manage and monitor cloud backup protection via the Spanning API.Apache 2.0
- AlicenseAqualityBmaintenanceMCP server for interacting with the ThreatLocker Portal API, enabling querying of computers, applications, policies, audit logs, and more through AI assistants.183GPL 3.0