AI IT Helpdesk Assistant MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| POSTGRES_DB | Yes | Database name. | |
| OPENAI_MODEL | No | Model name to use, e.g., gpt-4o-mini or llama-3.3-70b-versatile. | |
| POSTGRES_HOST | Yes | Database host. Use 'postgres' when running with Docker Compose, or 'localhost' for local runs. | |
| POSTGRES_PORT | Yes | Database port. Default in project is 5433. | |
| POSTGRES_USER | Yes | Database user. | |
| OPENAI_API_KEY | Yes | Your LLM API key. Required for the chat service. | |
| OPENAI_BASE_URL | No | Base URL for the OpenAI-compatible API. See README for provider examples (e.g., Groq, Gemini, OpenAI). | |
| SLACK_BOT_TOKEN | No | Slack bot token for bot_token mode. Optional; if not set, webhook mode or dry-run mode are used. | |
| MCP_ALLOWED_HOSTS | No | Comma-separated list of allowed hosts for MCP connections (DNS rebinding protection). Add any hostnames that will connect to the MCP endpoint. | |
| POSTGRES_PASSWORD | Yes | Database password. | |
| SLACK_WEBHOOK_URL | No | Slack webhook URL for webhook mode. Optional; if not set, bot_token mode or dry-run mode are used. |
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
ActivitySlowing
ResponsivenessNo issues