Support Triage MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_MODEL | No | Model for triage and Q&A when using Groq. | openai/gpt-oss-20b |
| OLLAMA_URL | No | URL of the local Ollama server when LLM_PROVIDER=ollama. | |
| MAX_TICKETS | No | Cap on queue size. | 600 |
| GROQ_API_KEY | No | API key for the default Groq provider. | |
| LLM_PROVIDER | No | LLM provider: groq (default) or ollama for a local model. | groq |
| OLLAMA_MODEL | No | Ollama model name when LLM_PROVIDER=ollama. | |
| TICKETS_PATH | No | Path to the tickets JSON file. | data/tickets.json |
| VECTOR_STORE | No | Vector store: numpy to skip FAISS, otherwise auto. | auto |
| EMBEDDING_MODEL | No | fastembed model name. | BAAI/bge-small-en-v1.5 |
| EMBEDDING_BACKEND | No | Embedding backend: fastembed, hashing or auto. | auto |
| RATE_LIMIT_PER_MIN | No | Per-client rate limit on endpoints that write or call the LLM. | 10 |
| DUPLICATE_THRESHOLD | No | Similarity threshold for duplicate detection; tune per embedder. | |
| RATE_LIMIT_GLOBAL_PER_MIN | No | Overall rate limit on endpoints that write or call the LLM. | 60 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues