# memspec MCP server

> Provides Git-backed project memory for AI coding agents with code-anchored verification and drift detection.

- Repository: https://github.com/siimvene/memspec
- Page: https://hostedmcp.org/servers/siimvene/memspec
- Transport: stdio
- Stars: 10
- License: MIT

## Install

### Claude Code

```sh
claude mcp add memspec -- npx -y memspec
```

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

```json
{
  "mcpServers": {
    "memspec": {
      "command": "npx",
      "args": [
        "-y",
        "memspec"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "memspec": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "memspec"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"memspec","type":"stdio","command":"npx","args":["-y","memspec"]}'
```

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

```json
{
  "mcpServers": {
    "memspec": {
      "command": "npx",
      "args": [
        "-y",
        "memspec"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add memspec -- npx -y memspec
```

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

```toml
[mcp_servers.memspec]
command = "npx"
args = ["-y", "memspec"]
```

### Gemini CLI

```sh
gemini mcp add -s user memspec npx -- -y memspec
```

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

```json
{
  "mcpServers": {
    "memspec": {
      "command": "npx",
      "args": [
        "-y",
        "memspec"
      ]
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MEMSPEC_DREAM_AUTOCOMMIT` | no | no |  |

## FAQ

### How does memspec handle code changes?

It ties memories to git blob SHAs and flags claims for review when the code drifts, preventing facts from rotting silently.

### Where is the memory data stored?

Memories are stored as human-readable markdown files with YAML frontmatter within a .memspec/ directory in your repository.

### Does memspec require a backend or cloud service?

No, it has zero infrastructure requirements, meaning no accounts, no API keys, and no hosted services are needed.
