# obsify MCP server

> Enables AI assistants to process sensitive files by providing schemas, synthetic twins, and local masked computation without exposing raw PII.

- Repository: https://github.com/Formative-Sum41/obsify
- Page: https://hostedmcp.org/servers/formative-sum41/obsify
- Transport: stdio
- Stars: 0
- License: MIT
- Latest version: 0.2.0

## Install

### Claude Code

```sh
claude mcp add obsify -- uvx obsify
```

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

```json
{
  "mcpServers": {
    "obsify": {
      "command": "uvx",
      "args": [
        "obsify"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "obsify": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "obsify"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"obsify","type":"stdio","command":"uvx","args":["obsify"]}'
```

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

```json
{
  "mcpServers": {
    "obsify": {
      "command": "uvx",
      "args": [
        "obsify"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add obsify -- uvx obsify
```

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

```toml
[mcp_servers.obsify]
command = "uvx"
args = ["obsify"]
```

### Gemini CLI

```sh
gemini mcp add -s user obsify uvx -- obsify
```

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

```json
{
  "mcpServers": {
    "obsify": {
      "command": "uvx",
      "args": [
        "obsify"
      ]
    }
  }
}
```

## FAQ

### Does the raw data leave my machine?

No, the server is local and deterministic. The model reasons over schemas and synthetic twins while the substance stays local.

### What file formats are supported?

It supports PDF (including tables), Excel (.xlsx/.xlsm), and Word (.docx) documents.

### How does it handle sensitive credentials?

It detects cloud keys, API tokens, private keys, and DB connection strings using anchored patterns rather than entropy heuristics to avoid false positives.
