Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MNEMO_DB_PATHNoDatabase path~/.mnemo/memory.db
MNEMO_DIMENSIONSNoEmbedding vector dimensions768
MNEMO_EMBEDDING_MODELNoEmbedding model namenomic-embed-text
MNEMO_EMBEDDING_API_KEYNoAPI key for cloud embedding providers (required if provider is openai)
MNEMO_EMBEDDING_BASE_URLNoAPI base URL for embedding providerhttp://localhost:11434
MNEMO_EMBEDDING_PROVIDERNoEmbedding provider: ollama or openaiollama

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememberB

Store a memory with optional tag, categories, and namespace

remember_batchA

Store multiple memories in a single call. Embeds all at once for efficiency. Deduplicates automatically.

recallC

Search memories semantically by query

forgetA

Delete a memory by ID

updateB

Update an existing memory's content or metadata. Re-embeds automatically if content changes.

bumpC

Reinforce a memory's weight (recall reinforcement)

decayB

Trigger a decay cycle — reduces memory weights based on tag tiers

inspectA

View a specific memory or aggregate stats

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/Skye-flyhigh/mnemo-mcp'

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