api-patterns
3CX's native PBX MCP server: the per-PBX endpoint shape (every PBX is its own FQDN and its own OAuth authorization server — there is no shared mcp.3cx.com),…
Mimecast message tracing: searching by sender, recipient, or subject; message states and message IDs; retrieving message metadata and headers; and holding or releasing messages.
$ npx -y skills add wyre-technology/msp-claude-plugins --skill message-tracking --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/message-trackingContext preview
The summary Claude sees to decide when to auto-load this skill.
Mimecast message tracing: searching by sender, recipient, or subject; message states and message IDs; retrieving message metadata and headers; and holding or releasing messages.
name: "Mimecast Message Tracking" description: > Mimecast message tracing: searching by sender, recipient, or subject; message states and message IDs; retrieving message metadata and headers; and holding or releasing messages. when_to_use: >- When tracing an email through Mimecast, or holding or releasing a message. Use when: mimecast message trace, mimecast track email, find message, trace email mimecast, mimecast hold, mimecast release, mimecast message search, mimecast delivery, mimecast rejected, or mimecast bounced.
Message tracking is the primary diagnostic tool in Mimecast for investigating email delivery issues, tracing suspicious messages, and managing held email. The Mimecast MCP server provides tools to search messages across the full delivery pipeline, retrieve detailed per-message metadata, and control message disposition (hold or release). This is the first tool to reach for when investigating reported phishing emails, delivery failures, or missing messages.
backlogged messages are a delivery condition, not a hold, and they are not searchable here until they land in a final state. Use `Mimecast Queue Management`.
attachment, and impersonation verdicts live in TTP; use `Mimecast Threat Intelligence`.
equivalent is the hold queue, and these message IDs address only it. Use `SpamTitan Quarantine`, `Proofpoint Quarantine`, or `Checkpoint Avanan Quarantine`.
attack** — Mimecast decides at the perimeter; behavioural detection after delivery is `Abnormal Security Threats`.
| State | Description | |-------|-------------| | `delivered` | Message successfully delivered to recipient mailbox | | `held` | Message blocked pending review (policy or manual) | | `rejected` | Message rejected at SMTP gateway | | `bounced` | Message accepted but returned by recipient server | | `processing` | Message in transit through the Mimecast pipeline |
Messages can be held by Mimecast policy (spam threshold, attachment policy, URL scanning) or placed on hold manually via the API. Held messages require an administrator action — either release them for delivery or permanently delete them.
Each message in Mimecast has:
When searching, you typically use sender/recipient/subject to find messages, then use the Mimecast ID for subsequent operations (get info, hold, release).
mimecast_find_message
Parameters:
**Example call:**
{
"from": "phishing@external-domain.com",
"to": "user@client.com",
"start": "2026-03-01T00:00:00Z",
"end": "2026-03-02T23:59:59Z",
"status": "delivered"
}**Example response:**
{
"meta": {
"status": 200,
"pagination": {
"pageSize": 25,
"totalCount": 3,
"next": null
}
},
"data": [
{
"id": "eNqrVkpJLU...",
"messageId": "<abc123@external-domain.com>",
"from": "phishing@external-domain.com",
"to": ["user@client.com"],
"subject": "Your account needs attention",
"status": "delivered",
"received": "2026-03-01T14:22:15Z",
"size": 48293,
"direction": "inbound"
}
]
}mimecast_get_message_info
Parameters:
**Example response:**
{
"meta": { "status": 200 },
"data": [
{
"id": "eNqrVkpJLU...",
"messageId": "<abc123@external-domain.com>",
"from": "phishing@external-domain.com",
"to": ["user@client.com"],
"subject": "Your account needs attention",
"status": "delivered",
"received": "2026-03-01T14:22:15Z",
"direction": "inbound",
"senderIP": "192.0.2.45",
"spamScore": 8,
"detectionLevel": "relaxed",
"attachments": [
{
"filename": "invoice.pdf",
"size": 42100,
"mimeType": "application/pdf"
}
],
"headers": {
"X-Originating-IP": "192.0.2.45",
"Return-Path": "bounce@external-domain.com",
"Authentication-Results": "spf=fail; dkim=fail; dmarc=fail"
},
"route": [
{
"action": "smtp_receive",
"timestamp": "2026-03-01T14:22:14Z",
"host": "mail.mimecast.com"
},
{
"action": "deliver",
"timestamp": "2026-03-01T14:22:15Z",
"host": "mail.client.com"
}
]
}
]
}Key fields to examine:
mimecast_hold_message
Places a message on hold to prevent delivery or further routing.
Parameters:
**Example response:**
{
"meta": { "status": 200 },
"data": [
{
"id": "eNqrVkpJLU...",One command to supercharge Claude Code for MSP workflows. Then restart Claude Code. That's it. Documentation: mcp.wyre.ai
Repo: wyre-technology/msp-claude-plugins
3CX's native PBX MCP server: the per-PBX endpoint shape (every PBX is its own FQDN and its own OAuth authorization server — there is no shared mcp.3cx.com),…
3CX's live-operations surface: read-only visibility into active calls, recordings, voicemail, department and queue membership, and forwarding/presence…
3CX's read-only directory surface: resolving a caller by email or by exact extension, searching the PBX's own phonebooks, searching contacts synced from an…
3CX's system-and-configuration surface: server time, PBX event log and application log search, service status, database schema and the read-only SELECT-only…
Abnormal Security abuse mailbox cases: user-reported email submissions, case statuses and judgments, the case lifecycle, bulk and remediation actions, and…
Abnormal Security message analysis: message retrieval, email header inspection, attachments, sender reputation, delivery context, and SPF/DKIM/DMARC…