proofpoint-mcp
The proofpoint-mcp server lets AI assistants query and act on Proofpoint TAP/Essentials security data for threat investigation, email tracing, quarantine, and reporting.
Discover domains and inspect credential/domain status (
proofpoint_navigate,proofpoint_status).Retrieve TAP threat data: all threats, delivered/blocked messages, permitted/blocked clicks.
Manage quarantine: list/search quarantined messages, release (high-impact) or delete (irreversible) them.
Look up threat intel: campaigns, threat details/interactive threat card, families, IOCs.
Handle DLP: list/get incidents and list encrypted messages.
Assess user risk: Very Attacked People (VAP), top clickers, user risk scores.
Perform forensics: threat/campaign evidence, message search, auto-pull (search & destroy).
Trace email via Smart Search: message tracking, message details, headers.
Manage policies: list/get email security policies and list routes.
Use URL Defense: decode Proofpoint-rewritten URLs and analyze URLs for threats.
Monitor events: list/detail/stats for spam, phish, malware, impostor detections.
Generate reports: organization, threat, mail flow, and executive summaries.
Proofpoint MCP Server
A Model Context Protocol (MCP) server for Proofpoint TAP and Essentials APIs. Enables AI assistants to investigate threats, trace emails, manage quarantine, access threat intelligence, and perform URL defense operations.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Proofpoint environment.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack. Built by MSPs, for MSPs.
Installation
npm install @wyre-ai/proofpoint-mcpRelated MCP server: knowbe4-mcp
Configuration
Copy .env.example and set the variables below. The stdio transport reads PROOFPOINT_* and does not use HTTP service-to-service auth.
Variable | Required | Description |
| For stdio and | Proofpoint TAP service principal |
| For stdio and | Proofpoint TAP service secret |
| No | API host. Defaults to |
| No |
|
| No |
|
| Yes for HTTP | Service-to-service 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 a real |
| No | HTTP port. Defaults to |
/health and /healthz stay unauthenticated and do not read credentials.
HTTP authentication
With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The check is verifyS2sHeader in src/s2s-verify.ts: 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 is HTTP 401, before vendor credentials are read.
In AUTH_MODE=gateway, /mcp also requires X-Proofpoint-Service-Principal and X-Proofpoint-Service-Secret (X-Proofpoint-Cluster-Url is optional). Those headers are the only credential source for that request. A request missing either required header returns 401 and does not fall back to PROOFPOINT_SERVICE_PRINCIPAL / PROOFPOINT_SERVICE_SECRET.
Usage
Running with Claude Desktop
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"proofpoint-mcp": {
"command": "npx",
"args": ["@wyre-ai/proofpoint-mcp"],
"env": {
"PROOFPOINT_SERVICE_PRINCIPAL": "your-proofpoint-service-principal"
"PROOFPOINT_SERVICE_SECRET": "your-proofpoint-service-secret"
}
}
}
}Running with Claude Code (CLI)
claude mcp add proofpoint-mcp \
-e PROOFPOINT_SERVICE_PRINCIPAL=your-value \
-e PROOFPOINT_SERVICE_SECRET=your-value \
-- npx -y @wyre-ai/proofpoint-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, Proofpoint credentials arrive on each request as headers; they are not read from the environment.
docker build -t proofpoint-mcp .
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-p 127.0.0.1:8080:8080 \
proofpoint-mcpCompose refuses to start when CONDUIT_S2S_SECRET is unset. The gateway service does not set PROOFPOINT_SERVICE_PRINCIPAL or PROOFPOINT_SERVICE_SECRET and does not use env_file, so a project .env cannot inject static vendor credentials. Compose still interpolates CONDUIT_S2S_SECRET from that file. It publishes 127.0.0.1:8080:8080:
CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" docker compose upSingle-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses PROOFPOINT_SERVICE_PRINCIPAL and PROOFPOINT_SERVICE_SECRET. It is separate from the gateway Compose service above.
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTH_MODE=env \
-e PROOFPOINT_SERVICE_PRINCIPAL=your-value \
-e PROOFPOINT_SERVICE_SECRET=your-value \
-p 127.0.0.1:8080:8080 \
proofpoint-mcpLocal HTTP without a secret is development-only. It binds 127.0.0.1 and logs a warning, even if MCP_HTTP_HOST is 0.0.0.0:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm startFeatures
Interactive Threat Card (MCP Apps)
proofpoint_threat_get_by_id renders as an interactive, read-only card in
MCP Apps hosts (Claude Desktop/web) showing the threat name, status,
category, severity, and resolved actor / malware-family / campaign names;
plain-JSON behavior is unchanged in other hosts. The card is neutral by
default and brandable via window.__BRAND__ injection or MCP_BRAND_* env
vars (MCP_BRAND_NAME, MCP_BRAND_LOGO_URL, MCP_BRAND_PRIMARY_COLOR,
MCP_BRAND_ACCENT_COLOR, MCP_BRAND_BG, MCP_BRAND_TEXT) — no rebuild
needed.
Available Domains
Dlp
Data loss prevention policies
Events
Security event stream and SIEM export
Forensics
Forensic analysis of threats
People
Very Attacked People (VAP) reporting
Policy
Email policy management
Quarantine
Email quarantine management
Reports
Security reports and summaries
Smart Search
Advanced email search
Tap
Targeted Attack Protection events and campaigns
Threat Intel
Threat intelligence and indicators of compromise
Url Defense
URL rewriting and click defense
Development
# Clone the repository
git clone https://github.com/WYRE-AI/proofpoint-mcp.git
cd proofpoint-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# HTTP refuses to start until CONDUIT_S2S_SECRET is a real secret
CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" MCP_TRANSPORT=http npm start
# Local HTTP only, without a service-to-service secret (always binds 127.0.0.1)
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm startContributing
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
40 toolsproofpoint_dlp_get_incidentA
Get detailed information about a specific DLP incident, including matched rules, sensitive data types, and message metadata.
Inputs: incident_id (required).
proofpoint_dlp_list_encryptedA
List messages that were encrypted by Proofpoint Email Encryption. Shows encrypted message status and recipient access.
Inputs: page, sender, endDate, per_page, +2 more.
proofpoint_dlp_list_incidentsA
List DLP incidents. Returns messages that triggered DLP rules, including policy violations and sensitive data detections.
Inputs: page, status, endDate, per_page, +2 more.
proofpoint_events_get_detailsA
Get detailed information about a specific detection event, including full threat analysis and message metadata.
Inputs: event_id (required).
proofpoint_events_get_statsA
Get detection event statistics. Returns counts of spam, phishing, malware, and impostor detections over a time period.
Inputs: interval, sinceTime, sinceSeconds.
proofpoint_events_listB
List spam, phishing, and malware detection events. Returns events where Proofpoint detected and acted on threats.
Inputs: interval, sinceTime, threatType, disposition, +1 more.
proofpoint_forensics_get_campaignA
Get forensic evidence for all threats in a campaign. Returns aggregated behavioral analysis across all associated threats.
Inputs: campaign_id (required).
proofpoint_forensics_get_threatA
Get forensic evidence for a specific threat. Returns behavioral analysis, network activity, file modifications, and other forensic indicators.
Inputs: threat_id (required), includeCampaignForensics.
proofpoint_forensics_pull_messagesA
Auto-pull (search & destroy) messages from mailboxes. This is a destructive operation that removes delivered messages from user mailboxes.
Inputs: message_ids (required), reason.
proofpoint_forensics_search_messagesB
Search for messages across mailboxes for threat response. Used for search & destroy / auto-pull operations to find and remediate delivered threats.
Inputs: sender, endDate, subject, startDate, +2 more.
proofpoint_people_get_top_clickersA
Get top clickers report. Returns users who clicked on the most threat URLs, indicating users who may need additional security training.
Inputs: page, size, window.
proofpoint_people_get_user_riskA
Get the risk score and attack details for a specific user by email address.
Inputs: email (required), window.
proofpoint_people_get_vapB
Get the Very Attacked People (VAP) report. Returns users who received the most attacks, ranked by attack index. Useful for identifying high-risk users.
Inputs: page, size, window.
proofpoint_policy_getA
Get detailed information about a specific policy including rules, conditions, and actions.
Inputs: policy_id (required).
proofpoint_policy_listA
List all email security policies. Returns policy names, types, and enabled status.
Inputs: type.
proofpoint_policy_list_routesA
List email routing rules/routes. Shows how mail is routed based on policy configuration.
Inputs: page, per_page.
proofpoint_quarantine_deleteADestructive
⚠ DESTRUCTIVE — IRREVERSIBLE. Permanently delete a quarantined message. This action cannot be undone and will remove the message from quarantine storage. Confirm with the user before invoking.
Inputs: message_id (required).
proofpoint_quarantine_listB
List quarantined messages. Returns messages held in quarantine with sender, recipient, subject, and reason.
Inputs: page, folder, sender, endDate, +4 more.
proofpoint_quarantine_releaseADestructiveIdempotent
⚠ HIGH-IMPACT. Release a quarantined message, delivering it to the intended recipient. Irreversible delivery but message itself is preserved. Can deliver malicious mail to user. Confirm with the user before invoking.
Inputs: message_id (required).
proofpoint_quarantine_searchA
Search quarantine by keyword across sender, recipient, and subject fields.
Inputs: query (required), page, endDate, per_page, +1 more.
proofpoint_reports_executive_summaryA
Get executive summary report. High-level security posture overview suitable for management reporting. Includes threat trends, top targeted users, and effectiveness metrics.
Inputs: window.
proofpoint_reports_mail_flowB
Get mail flow report. Shows email volume over time with breakdown by disposition (delivered, blocked, quarantined).
Inputs: window, granularity.
proofpoint_reports_org_summaryA
Get organization security summary. Returns high-level metrics: total messages processed, threats blocked, quarantined, and delivered.
Inputs: window.
proofpoint_reports_threat_summaryB
Get threat summary report. Breakdown of threats by type (spam, phishing, malware, impostor) with counts and trends.
Inputs: window, threatType.
proofpoint_smart_search_get_headersB
Get the full email headers for a specific message.
Inputs: message_id (required).
proofpoint_smart_search_get_messageB
Get detailed information about a specific message including headers, processing log, and delivery details.
Inputs: message_id (required).
proofpoint_smart_search_traceA
Trace messages through the Proofpoint mail flow. Search by sender, recipient, subject, or message ID to track delivery status and processing history.
Inputs: page, sender, status, endDate, +5 more.
proofpoint_statusA
Show credentials status and available domains
Inputs: no named parameters.
proofpoint_tap_get_all_threatsB
Get all threats (messages and clicks) from the TAP SIEM API for a given time window. Returns both delivered/blocked messages and permitted/blocked clicks.
Inputs: format, interval, sinceTime, sinceSeconds, +1 more.
proofpoint_tap_get_clicks_blockedB
Get blocked clicks on threat URLs. These are clicks that were prevented from reaching the malicious destination.
Inputs: interval, sinceTime, sinceSeconds, threatStatus.
proofpoint_tap_get_clicks_permittedA
Get permitted clicks on threat URLs. These are clicks that were allowed through to the destination.
Inputs: interval, sinceTime, sinceSeconds, threatStatus.
proofpoint_tap_get_messages_blockedB
Get messages blocked that contained threats. These are messages quarantined or rejected before reaching the recipient.
Inputs: interval, sinceTime, sinceSeconds, threatStatus.
proofpoint_tap_get_messages_deliveredA
Get messages delivered containing threats. These are messages that reached the recipient's mailbox despite containing identified threats.
Inputs: interval, sinceTime, sinceSeconds, threatStatus.
proofpoint_threat_get_by_idA
Get detailed information about a specific threat by its threat ID. Returns threat type, classification, and associated indicators.
Inputs: threat_id (required).
proofpoint_threat_get_campaignA
Get details of a specific threat campaign by campaign ID. Returns campaign actors, malware families, techniques, and associated messages.
Inputs: campaign_id (required).
proofpoint_threat_get_iocsA
Get indicators of compromise (IOCs) for a specific campaign or time range. Returns URLs, IPs, domains, file hashes associated with threats.
Inputs: interval, sinceTime, campaign_id, threat_type.
proofpoint_threat_list_familiesB
List known threat families tracked by Proofpoint. Returns malware family names, descriptions, and associated campaigns.
Inputs: interval, sinceTime.
proofpoint_url_analyzeB
Analyze a URL for threats. Returns threat classification, risk score, and associated campaigns.
Inputs: url (required).
proofpoint_url_decodeA
Decode one or more Proofpoint URL Defense rewritten URLs back to the original URLs. Proofpoint rewrites URLs in emails for click-time protection; this tool reverses that encoding.
Inputs: urls (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 40 tools
Tools are grouped by domain with detailed descriptions, but overlap exists between threat and forensics tools (e.g., threat_get_campaign vs forensics_get_campaign), between TAP all-threats and message/click-specific retrievals, and between multiple report/event summary tools. The sheer number of similarly-shaped list/get/report tools leaves room for misselection without careful reading.
Nearly all tools follow a proofpoint_<domain>_<action/object> snake_case pattern, with clear domain prefixes making navigation predictable. Minor inconsistencies include report tools using noun phrases like reports_threat_summary instead of action verbs, and standalone tools like proofpoint_navigate and proofpoint_status that don't follow the domain-action pattern.
With 40 tools, the surface is heavy and exceeds the typical well-scoped range for an agent toolkit. While Proofpoint is a broad platform and each domain has only a few tools, exposing all of them under one server creates a large, potentially unwieldy namespace. It isn't extreme enough for a 1, but is clearly in the 'too many' range.
The server covers major Proofpoint domains well: quarantine lifecycle, TAP events, DLP incidents, forensic search and pull, smart search, reporting, policy read access, URL handling, and detection events. However, the policy and threat-response surfaces are read-mostly, with no create/update/delete policy, no blocklist/sender remediation, and limited actions beyond forensics pull. This leaves notable admin and response gaps.
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.
Cybersecurity MCP server for URL scanning, threat intelligence, and domain reputation.
Hosted MCP server for your Gmail, Outlook and IMAP mail, with mailboxes and scopes set per agent.
Related MCP Servers
- 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
- AlicenseBqualityBmaintenanceMCP server for KnowBe4 — security awareness training, phishing simulation, and user risk management API integration30Apache 2.0
- AlicenseAqualityCmaintenanceMCP server for Ironscales — phishing incident management, email classification, and remediation2Apache 2.0
- AlicenseAqualityBmaintenanceMCP server for SpamTitan email security — manage quarantine, allowlists, blocklists, and view email stats9Apache 2.0