Schema | mcp-memory

mcp-memory

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PORT`	No	Port for the MCP server.	3000
`AWS_REGION`	No	AWS region for S3 buckets.	ap-northeast-2
`MCP_API_KEY`	No	When set, every request must present it as a bearer token. If unset, no authentication is required.
`STATE_BUCKET`	Yes	Ordinary S3 bucket for counters and the recency index. Required.
`VECTOR_INDEX`	No	Index within the S3 Vectors bucket.	memories
`EMBEDDING_DIM`	No	Embedding dimension; must match the index's dimension (1024 for Titan v2, 1536 for OpenAI).	1024
`VECTOR_BUCKET`	Yes	S3 Vectors bucket holding the memories. Required.
`STATS_FLUSH_MS`	No	How often a pod pushes its counters.	30000
`EMBEDDING_MODEL`	No	Embedding model name (e.g., 'text-embedding-3-small' for OpenAI).	amazon.titan-embed-text-v2:0
`EMBEDDING_API_KEY`	No	API key for OpenAI-compatible embedding service. Required when EMBEDDING_PROVIDER is 'openai'.
`EMBEDDING_BASE_URL`	No	OpenAI-compatible base URL. Required when EMBEDDING_PROVIDER is 'openai'.
`EMBEDDING_PROVIDER`	No	The embedding provider: 'bedrock' or 'openai'.	bedrock
`RECALL_MIN_SIMILARITY`	No	Relevance floor for recall; model-specific.	0.1
`STATS_COMPACT_THRESHOLD`	No	Shard count past which a reader folds them in.	20

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

ActivityActive

ResponsivenessNo issues