Skip to main content
Glama
PankajMahanto

AI IT Helpdesk Assistant MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
POSTGRES_DBYesDatabase name.
OPENAI_MODELNoModel name to use, e.g., gpt-4o-mini or llama-3.3-70b-versatile.
POSTGRES_HOSTYesDatabase host. Use 'postgres' when running with Docker Compose, or 'localhost' for local runs.
POSTGRES_PORTYesDatabase port. Default in project is 5433.
POSTGRES_USERYesDatabase user.
OPENAI_API_KEYYesYour LLM API key. Required for the chat service.
OPENAI_BASE_URLNoBase URL for the OpenAI-compatible API. See README for provider examples (e.g., Groq, Gemini, OpenAI).
SLACK_BOT_TOKENNoSlack bot token for bot_token mode. Optional; if not set, webhook mode or dry-run mode are used.
MCP_ALLOWED_HOSTSNoComma-separated list of allowed hosts for MCP connections (DNS rebinding protection). Add any hostnames that will connect to the MCP endpoint.
POSTGRES_PASSWORDYesDatabase password.
SLACK_WEBHOOK_URLNoSlack webhook URL for webhook mode. Optional; if not set, bot_token mode or dry-run mode are used.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PankajMahanto/AI-IT-Helpdesk'

If you have feedback or need assistance with the MCP directory API, please join our Discord server