Support Ticket Triage MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRIAGE_DATA_ROOT | No | Root directory for runtime data (default: data/runtime) | |
| TRIAGE_SEED_FILE | No | Path to seed tickets JSON file (default: data/seed/tickets.json) | |
| TRIAGE_MINUTES_SAVED | No | Minutes saved per accepted recommendation (default: 8) | |
| TRIAGE_KNOWLEDGE_ROOT | No | Root directory for knowledge articles (default: data/knowledge) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_ticketsB | Filter and page through the local support ticket queue. |
| get_ticketA | Read one support ticket by ID. |
| search_knowledgeA | Search local support knowledge and policy articles. |
| find_similar_ticketsA | Find likely duplicate tickets using deterministic text similarity. |
| get_queue_metricsA | Calculate current queue, SLA, recommendation, and savings metrics. |
| get_audit_eventsB | Read all audit events or events for one ticket. |
| submit_triage_recommendationA | Store a local triage proposal without changing the ticket or external systems. |
| approve_triage_recommendationC | Apply only explicitly approved recommendation fields to the ticket. |
| reject_triage_recommendationB | Finalize a local triage proposal as rejected and record feedback. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| triage_ticket | Prepare a governed recommendation for one ticket. |
| triage_queue | Prepare governed recommendations for a bounded ticket batch. |
| review_escalations | Review tickets that may require security, outage, confidence, or SLA escalation. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| queue-metrics | Current support queue metrics as stable JSON. |
TDQS
Scored across 9 tools
Each tool targets a distinct resource or action: list/get tickets differ from search/find, and the triage workflow has clear submit/approve/reject stages. No two tools share the same purpose or even overlap ambiguously.
All tool names follow a consistent verb_noun pattern in snake_case (list_tickets, search_knowledge, submit_triage_recommendation). The verbs are varied but predictable, and there are no mixed naming conventions or cryptic abbreviations.
9 tools is well within the ideal 3-15 range. Each tool covers a necessary part of the ticket triage workflow—querying, analysis, auditing, and recommendation lifecycle—without redundancy or bloat.
The core triage workflow is well-covered: ticket retrieval, duplicate detection, knowledge search, metrics, audit, and recommendation submit/approve/reject. A minor gap is the lack of a dedicated tool to retrieve or list existing recommendations, which could force agents to rely on audit events.