Memanto — Claude Code MCP server: what it does, how to install
Adds persistent semantic memory to MCP agents so they retain decisions, preferences, and project context across separate chat sessions.
claude mcp add memanto -- uvx memanto-mcpWhat Memanto does
The server connects Memanto primitives to MCP client environments. It registers seven core tools out of the box: remember for single entries, batch_remember for up to 100 records at once, recall for semantic search, along with recency and point-in-time filters. The answer tool synthesizes grounded responses directly from stored memory items.
Every record tracks its author via the client handshake (cursor, claude_code, codex), keeping editor contributions organized inside the shared namespace. Setting MEMANTO_EXPOSE_ADMIN=true activates four additional management tools to create, inspect, and delete agent namespaces.
Running this server requires a MOORCHEH_API_KEY and Python 3.10 or higher. When deployed over network transports like SSE or Streamable HTTP, the process handles upstream authentication to Moorcheh but does not verify incoming client requests.
What it helps with
- persist coding preferences and architecture choices across sessions
- retrieve past technical decisions using semantic search with
recall - ingest up to 100 facts in a single call from project documentation
- attribute memory entries to specific clients like Cursor or Claude Code
Example prompts for the agent
- Remember that this repository uses uv for dependency management.
- Recall our previous decisions regarding database migrations.
- What project guidelines have changed since our last session?
How to install Memanto
Platform CLI
claude mcp add memanto -- uvx memanto-mcpuvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>
Platform CLI
codex mcp add mcp -- uvx memanto-mcpuvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>
Config file
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"memanto-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>
Config file
{
"servers": {
"mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"memanto-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>
Platform CLI
gemini mcp add mcp uvx memanto-mcpuvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Memanto
How do I install Memanto in Claude Code?
Run claude mcp add memanto -- uvx memanto-mcp. Make sure to set MOORCHEH_API_KEY in your environment or project .env file.
What does the Memanto MCP server do?
It gives AI assistants tools to store facts, retrieve context via semantic search, and synthesize answers based on long-term project knowledge.
What are the requirements to run Memanto?
The server requires Python 3.10+, package versions memanto>=0.2.13 and mcp>=1.2,<2, plus a valid MOORCHEH_API_KEY.
