The memory-mcp server provides AI agents with persistent memory management using Letta's data platform. It exposes tools for storing, retrieving, and managing memory entries. The server connects to Letta's data platform via its API, allowing agents to interact with memory data. Developers use this server to build AI agents that require long-term memory, such as chatbots, personal assistants, or any application needing context retention.
The memory-mcp server provides AI agents with persistent memory management using Letta's data platform. It exposes tools for storing, retrieving, and managing memory entries. The server connects to Letta's data platform via its API, allowing agents to interact with memory data. Developers use this server to build AI agents that require long-term memory, such as chatbots, personal assistants, or any application needing context retention.
npx -y @letta-ai/memory-mcpAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"letta-ai-memory-mcp-npm": {
"command": "npx",
"args": [
"-y",
"npx -y @letta-ai/memory-mcp"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from memory-mcp?"
No configuration required. This server works out of the box.
"What resources are available in memory-mcp?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in memory-mcp"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in memory-mcp with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.