MCP server for remote management of project memory banks
If you already use Memory, the memory mcp server is the piece that lets your assistant work with it directly. MCP server for remote management of project memory banks.
A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
The Memory Bank MCP Server transforms traditional file-based memory banks into a centralized service that:
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Multi — Project Support**Project — specific directoriesType — safe operationsMEMORY_BANK_ROOT — Directory where project memory banks will be stored (e.g., /path/to/memory-bank)disabled — Set to false to enable the serverautoApprove — List of operations that don't require explicit user approval:memory_bank_read — Read memory bank filesmemory_bank_write — Create new memory bank filesmemory_bank_update — Update existing memory bank fileslist_projects — List available projectslist_project_files — List files within a projectTesting — The Testing tool exposed by this serverConfiguration is passed through the environment: MEMORY_BANK_ROOT. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Memory's toolset — Multi, Project, Type and 9 more — is a fair guide to whether it matches your workflow. It is maintained by arpepper; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Memory's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Multi | Project Support** |
| Project | specific directories |
| Type | safe operations |
| MEMORY_BANK_ROOT | Directory where project memory banks will be stored (e.g., /path/to/memory-bank) |
| disabled | Set to false to enable the server |
| autoApprove | List of operations that don't require explicit user approval: |
| memory_bank_read | Read memory bank files |
| memory_bank_write | Create new memory bank files |
| memory_bank_update | Update existing memory bank files |
| list_projects | List available projects |
| list_project_files | List files within a project |
| Testing | The Testing tool exposed by this server. |
{
"mcpServers": {
"memory-bank": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"MEMORY_BANK_ROOT": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| MEMORY_BANK_ROOT | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.