Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort for the MCP server.3000
AWS_REGIONNoAWS region for S3 buckets.ap-northeast-2
MCP_API_KEYNoWhen set, every request must present it as a bearer token. If unset, no authentication is required.
STATE_BUCKETYesOrdinary S3 bucket for counters and the recency index. Required.
VECTOR_INDEXNoIndex within the S3 Vectors bucket.memories
EMBEDDING_DIMNoEmbedding dimension; must match the index's dimension (1024 for Titan v2, 1536 for OpenAI).1024
VECTOR_BUCKETYesS3 Vectors bucket holding the memories. Required.
STATS_FLUSH_MSNoHow often a pod pushes its counters.30000
EMBEDDING_MODELNoEmbedding model name (e.g., 'text-embedding-3-small' for OpenAI).amazon.titan-embed-text-v2:0
EMBEDDING_API_KEYNoAPI key for OpenAI-compatible embedding service. Required when EMBEDDING_PROVIDER is 'openai'.
EMBEDDING_BASE_URLNoOpenAI-compatible base URL. Required when EMBEDDING_PROVIDER is 'openai'.
EMBEDDING_PROVIDERNoThe embedding provider: 'bedrock' or 'openai'.bedrock
RECALL_MIN_SIMILARITYNoRelevance floor for recall; model-specific.0.1
STATS_COMPACT_THRESHOLDNoShard count past which a reader folds them in.20

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/opspresso/mcp-memory'

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