Schema | MCP Memory Service - TypeScript

MCP Memory Service - TypeScript

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LOG_LEVEL`	No	Logging level for the server. Options: debug, info, warn, error	info
`MCP_DEBUG`	No	Set to 1 to enable detailed MCP protocol debugging
`TURSO_URL`	Yes	The URL for your Turso database (e.g., libsql://your-database.turso.io)
`OPENAI_API_KEY`	Yes	Your OpenAI API key used for generating vector embeddings
`CLERK_SECRET_KEY`	No	Clerk secret key for authentication in remote/web mode
`GOOGLE_CLIENT_ID`	No	Google Cloud Client ID for Google Contacts/Calendar integration
`TURSO_AUTH_TOKEN`	Yes	Your Turso database authentication token
`DEFAULT_USER_EMAIL`	No	The default user email used for memory context and identification
`GOOGLE_REDIRECT_URI`	No	The redirect URI for Google OAuth callback
`GOOGLE_CLIENT_SECRET`	No	Google Cloud Client Secret for Google Contacts/Calendar integration
`ENABLE_EMBEDDING_MONITOR`	No	Enables background monitoring for automatic embedding updates	true
`EMBEDDING_MONITOR_INTERVAL`	No	The interval in milliseconds to check for embedding updates	60000
`NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY`	No	Clerk publishable key for authentication in remote/web mode

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

ActivityInactive

ResponsivenessNo issues