# agentmemorymcp-mcp

A hosted remote memory service for AI agents. It stores observations, queries graph relationships, and records audit logs across development sessions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: clauxel
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/clauxel/agentmemory-mesh-mcp
- Updated: 2026-05-21
- HTML: https://affpapa.org/en/nevibecode/mcp/agentmemorymcp-mcp

## What it does

The server operates over HTTP at `https://agentmemorymcp.clauxel.com/mcp`. Four remote tools are available: `memory_smart_search`, `memory_save_observation`, `memory_session_summary`, and `memory_graph_query`. They help agents retrieve past context and inspect connected facts.

Production calls require a bearer token. Without `Authorization: Bearer <token>`, the endpoint responds with a JSON error. The public repository provides documentation only, keeping the backend private.

## Requirements
- Remote server: `https://agentmemorymcp.clauxel.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http agentmemorymcp-mcp https://agentmemorymcp.clauxel.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add agentmemorymcp-mcp --url https://agentmemorymcp.clauxel.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "agentmemorymcp-mcp": {
            "url": "https://agentmemorymcp.clauxel.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "agentmemorymcp-mcp": {
            "type": "http",
            "url": "https://agentmemorymcp.clauxel.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http agentmemorymcp-mcp https://agentmemorymcp.clauxel.com/mcp
```

## When to use it
- store runtime agent observations using `memory_save_observation`
- retrieve relevant past context with `memory_smart_search`
- generate structured session summaries for agent workflows
- inspect entity connections through `memory_graph_query`

## Example prompts
- Record the key design decisions from our refactoring session into memory
- Search previous agent memories for API credential formats
- Query the memory graph for dependencies between the auth and payment modules

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 397855
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 34011
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81191
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119324
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47670
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43929

---
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