LibSQL-based persistent memory tool for MCP
If you want an AI assistant working directly with MCP Memory Libsql, the mcp memory libsql mcp server is the bridge. LibSQL-based persistent memory tool for MCP.
A high-performance, persistent memory system for the Model Context Protocol (MCP) powered by libSQL. This server provides vector search capabilities and efficient knowledge storage using libSQL as the backing store.
Once connected, the assistant can call this tool directly:
Publishing — Due to npm 2FA requirements, publishing needs to be done manually:The server is distributed via npm as mcp-memory-libsql, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply 2 environment variables: LIBSQL_URL, LIBSQL_AUTH_TOKEN. Keep credentials in your client's env block or a secrets manager rather than committing them.
Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. MCP Memory Libsql sits in that group, and the shape of its toolset — Publishing — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Publishing | Due to npm 2FA requirements, publishing needs to be done manually: |
{
"mcpServers": {
"mcp-memory-libsql": {
"command": "npx",
"args": ["-y", "mcp-memory-libsql"],
"env": {
"LIBSQL_URL": "file:/path/to/your/database.db"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| LIBSQL_URL | Endpoint or connection string the server talks to. | Yes |
| LIBSQL_AUTH_TOKEN | Credential the server authenticates with. | Yes |
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.