Schema | supermem

supermem

Describes the environment variables required to run the server.

Name	Required	Description
`OLLAMA_HOST`	No	Ollama server URL (default: 'http://localhost:11434')
`LMSTUDIO_HOST`	No	LM Studio server URL (default: 'http://localhost:1234')
`SUPERMEM_VECTOR`	No	Set 'true' to enable ChromaDB vector tier (default: 'false')
`SUPERMEM_API_KEY`	No	Bearer token for HTTP API auth (disabled if unset)
`SUPERMEM_DB_PATH`	No	SQLite database path (default: '~/.supermem/supermem.db')
`ANTHROPIC_API_KEY`	No	Required if provider is 'claude'
`OPENROUTER_API_KEY`	No	Required if provider is 'openrouter' (or default)
`SUPERMEM_LLM_MODEL`	No	Model string (provider default if not set)
`SUPERMEM_RATE_LIMIT`	No	Requests/minute limit (default: '60')
`SUPERMEM_VAULT_PATH`	Yes	Path to the markdown vault directory (required, no default)
`SUPERMEM_WORKER_PORT`	No	HTTP dashboard port (default: '37777')
`SUPERMEM_LLM_PROVIDER`	No	LLM provider (default: 'openrouter'); options: 'openrouter', 'ollama', 'claude', 'lmstudio'
`SUPERMEM_COMPRESS_EVERY`	No	Observations written before LLM compression (default: '50')

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

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lamenting-hawthorn/supermem'

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