Schema | MCP Memory Server

MCP Memory Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_MEMORY_PATH`	Yes	The absolute path where memories are saved to disk (e.g., /path/to/mcp-memory-server/mcp_memory_data).

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 }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
memory_searchA	Search the semantic memory for a specific project using a natural language query.
memory_addB	Add a new memory fragment/document to the project's vector store.
memory_list_sourcesB	List all files/sources ingested for a project.
memory_delete_sourceB	Delete all memories associated with a specific file source.
memory_statsC	Get statistics for a project's memory (chunk count).
memory_resetC	Reset (clear) all memories for a project.

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/iamjpsharma/fremem'

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