Schema | Insight AI-SQL MCP Server

Insight AI-SQL MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`ADMIN_PORT`	No	Port for the admin panel	8001
`POSTGRES_DB`	No	PostgreSQL database name	fraud_db
`SQL_MAX_ROWS`	No	Maximum rows returned by SQL queries (defensive limit)	100
`POSTGRES_HOST`	Yes	PostgreSQL host
`POSTGRES_PORT`	No	PostgreSQL port	5432
`POSTGRES_USER`	Yes	PostgreSQL user
`SQL_MAX_RETRIES`	No	Maximum number of retries on SQL failure	3
`ADMIN_SECRET_KEY`	No	Secret key for signing admin session cookies (auto-generated if not set)
`POSTGRES_PASSWORD`	Yes	PostgreSQL password
`SQL_DEBUG_CONTEXT`	No	Enable debug context in SQL generation (True/False)	False
`AZURE_OPENAI_API_KEY`	Yes	Azure OpenAI API key
`AZURE_SEARCH_API_KEY`	Yes	Azure AI Search API key
`AZURE_OPENAI_ENDPOINT`	Yes	Azure OpenAI endpoint URL (may point to Foundry project)
`AZURE_SEARCH_ENDPOINT`	Yes	Azure AI Search endpoint URL
`AZURE_SEARCH_INDEX_NAME`	Yes	Azure AI Search index name
`AZURE_OPENAI_API_VERSION`	Yes	Azure OpenAI API version
`AZURE_OPENAI_CHAT_DEPLOYMENT`	Yes	Azure OpenAI chat deployment name
`AZURE_OPENAI_EMBEDDING_DEPLOYMENT`	Yes	Azure OpenAI embedding deployment name

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivitySlowing

ResponsivenessNo issues