A Model Context Protocol (MCP) server that provides persistent memory capabilities for Large Language Models. Store concepts, code snippets, notes, and any information you want your LLM to remember…
MCP Memory Server is an MCP project maintained in the jvreagan/mcp-memory-server repository. The maintainer describes its purpose as “A Model Context Protocol (MCP) server that provides persistent memory capabilities for Large Language Models. Store concepts, code snippets, notes, and any information you want…”. Read the project documentation for the complete scope.
The project provides a local client configuration using /absolute/path/to/your/mcp-memory-server. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
The example declares MCP_DATA_DIR. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| remember | Store new information |
| recall | Search stored memories |
| forget | Delete a memory by ID |
| list_memories | List all memories with filtering |
| memory_stats | Get usage statistics |
{
"mcpServers": {
"memory": {
"command": "/absolute/path/to/your/mcp-memory-server",
"args": [],
"env": {
"MCP_DATA_DIR": "/Users/yourusername/.mcp-memory"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| MCP_DATA_DIR | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
A low-level server implementation using the Model Context Protocol (MCP) with streamable HTTP support.
An MCP (Model Context Protocol) server that provides access to AIND (Allen Institute for Neural Dynamics) metadata and data assets through a
Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.