Schema | mem0-mcp-server

mem0-mcp-server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MEM0_DIR`	No	Where memory data is stored.	~/.mem0
`OPENAI_API_KEY`	No	Set to use OpenAI embeddings (1536 dims). If not set, the server falls back to FastEmbed, Ollama, or MockEmbeddings.
`MEM0_LOCAL_OLLAMA_URL`	No	Ollama base URL.	http://localhost:11434
`MEM0_LOCAL_OLLAMA_MODEL`	No	Ollama model name.	nomic-embed-text
`MEM0_LOCAL_FASTEMBED_MODEL`	No	FastEmbed model name.	BAAI/bge-small-zh-v1.5

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }

Functions exposed to the LLM to take actions

Name	Description
add_memoryA	Store a memory in the local OSS Mem0 store. By default the text is stored verbatim with no LLM call (offline, free). Set infer=true to run Mem0's LLM fact extraction (requires a configured LLM).
search_memoriesB	Search memories by semantic similarity. Uses local embeddings.
get_memoriesA	List stored memories, newest first, with optional user/agent filters.
get_memoryB	Retrieve a single memory by its ID.
update_memoryB	Overwrite the text (and optionally metadata) of a memory by ID.
delete_memoryA	Delete a single memory by ID.
delete_all_memoriesA	Delete all memories for a user and/or agent. At least one scope is required.

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/zfy258/mem0-mcp-server'

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