# Memanto

Adds persistent semantic memory to MCP agents so they retain decisions, preferences, and project context across separate chat sessions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2340
- Author: moorcheh-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/moorcheh-ai/memanto/tree/HEAD/integrations/mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/memanto

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add memanto -- uvx memanto-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add mcp -- uvx memanto-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add mcp uvx memanto-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from memanto-mcp <command>

## When to use it
- 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
- 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?

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md