# codeagent-memory MCP server

> Provides a local code graph and conversational memory system for coding agents using tree-sitter symbols and hybrid RRF retrieval.

- Repository: https://github.com/HanochZhu/codeagent_memory
- Page: https://hostedmcp.org/servers/hanochzhu/codeagent-memory
- Transport: stdio
- Stars: 1
- License: MIT
- Latest version: 0.1.6

## Install

### Claude Code

```sh
claude mcp add codeagent-memory -- docker run -i --rm ghcr.io/hanochzhu/codeagent-memory:0.1.6
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "codeagent-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/hanochzhu/codeagent-memory:0.1.6"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "codeagent-memory": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/hanochzhu/codeagent-memory:0.1.6"
      ]
    }
  }
}
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "codeagent-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/hanochzhu/codeagent-memory:0.1.6"
      ]
    }
  }
}
```

### Codex (`~/.codex/config.toml`)

```toml
[mcp_servers.codeagent-memory]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/hanochzhu/codeagent-memory:0.1.6"]
```

### Gemini CLI (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "codeagent-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/hanochzhu/codeagent-memory:0.1.6"
      ]
    }
  }
}
```

## FAQ

### Is the data stored locally or in the cloud?

The system is 100% local and private, using local SQLite and on-disk embeddings with zero external API costs.

### How can I connect it to my coding agent?

You can register the MCP stdio command 'cam' with the argument 'mcp' in your IDE's MCP configuration.