RomM MCP Server

An MCP server for RomM — the self-hosted retro game library manager. 40 tools: 26 read-only for browsing platforms, searching ROMs, viewing metadata, collections (regular, smart, and virtual), saves, play activity, and tasks — plus 14 write tools for play status, play sessions, favorites, notes, and collection management, through any MCP-compatible AI assistant.

Tools

Read

Write

These modify your own user data and collections. They cannot alter ROM files, platforms, firmware, other users, or save files.

Related MCP server: proxy-mcp

Setup

Prerequisites

• Python 3.10+

• A running RomM instance (v5.0+; most read tools also work on v4.4+)

• An enabled RomM user account — admin is not required (see Auth)

Install

pip install fastmcp httpx

Or clone and install:

git clone https://github.com/lodordev/mcp-romm.git
cd mcp-romm
pip install .

Configure

Set environment variables:

Add to Claude Code

Add to your .mcp.json:

{
  "mcpServers": {
    "romm": {
      "command": "python",
      "args": ["/path/to/mcp-romm/server.py"],
      "env": {
        "ROMM_URL": "http://your-romm-instance:3000",
        "ROMM_USERNAME": "your-username",
        "ROMM_PASSWORD": "your-password"
      }
    }
  }
}

Add to Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "romm": {
      "command": "python",
      "args": ["/path/to/mcp-romm/server.py"],
      "env": {
        "ROMM_URL": "http://your-romm-instance:3000",
        "ROMM_USERNAME": "your-username",
        "ROMM_PASSWORD": "your-password"
      }
    }
  }
}

Remote (HTTP) transport

By default the server speaks stdio and is spawned by the client. To host it as a shared network service instead — e.g. one instance on your homelab that all your machines use — set:

ROMM_MCP_TRANSPORT=http ROMM_MCP_HOST=0.0.0.0 ROMM_MCP_PORT=8765 python server.py

Then point clients at it, e.g. Claude Code:

claude mcp add --transport http romm http://your-host:8765/mcp

The HTTP transport has no authentication of its own — bind it to a trusted network only (LAN, VPN, or an overlay network like Tailscale), never the open internet. Note that claude.ai web/mobile connectors connect from Anthropic's cloud and cannot reach private-network URLs.

Examples

Once configured, you can ask your AI assistant things like:

• "What platforms do I have in RomM?"

• "Search for Zelda games"

• "Show me my backlog"

• "How many ROMs do I have total?"

• "What was recently added?"

• "Show me the saves for Super Metroid"

• "What's in my favorites?"

• "List my firmware files for PlayStation"

• "What tasks are running?"

• "What devices are registered?"

And, with the write tools:

• "Mark Chrono Trigger as finished"

• "Favorite Super Metroid"

• "Add it to my backlog and rate it 9"

• "Make a collection called 'SNES RPGs' and add ROMs 10, 11, and 12"

• "Add a note to this ROM: 'glitch at the second boss, save often'"

Security

• Least privilege. The OAuth2 token requests only the read scopes the tools use plus roms.user.write, collections.write, and tasks.run. It deliberately does not request roms.write, platforms.write, firmware.write, assets.write, users.write, or me.write — no tool uses them.

• Bounded write surface. Write tools change only your own user data (play status, favorites, notes) and your own collections. No tool edits ROM files, platforms, firmware, other users, or uploads/deletes save files.

• Destructive ops are labeled. romm_delete_note and romm_delete_collection permanently remove data and say so in their descriptions. (romm_delete_collection removes the grouping, not the ROMs.)

• No disk writes. Credentials and tokens are held in memory only, never written to disk.

• TLS by default. Certificate verification is enabled by default (ROMM_TLS_VERIFY=true).

• Auto-retry. If a token expires mid-session, the server re-authenticates transparently.

Auth

The server uses OAuth2 password grant to authenticate with RomM. Tokens are scoped to the minimum permissions needed and automatically refreshed when they expire. If a request gets a 401, the server re-authenticates and retries once.

Note: The read and write tools operate on your own library and user data, so an ordinary enabled RomM user account is sufficient — admin is not required. (romm_scan_library does require an account permitted to run tasks.)

RomM 5.0 role change: RomM 5.0 collapsed the old viewer/editor/admin roles into user/admin and moved fine-grained authorization to a permissions system (legacy roles are coerced to user on upgrade). If a tool unexpectedly gets a 403 on a 5.0 instance, check the account's effective permissions (GET /api/permissions/me) in the RomM admin UI.

Known issues

All three are RomM 5.0.0 server-side issues, found by running this server's live e2e suite (smoke_test.py) against a 5.0.0 instance:

• romm_filters times out. GET /api/roms/filters in RomM 5.0.0 executes a query with a cartesian product (RomM's log flags it at roms_handler.py:2159); the request hangs until the client timeout, and the abandoned query keeps running server-side at high CPU. Avoid calling romm_filters on 5.0.0 until this is fixed upstream — every call strands another runaway database query.

• Note listing 500s once any note exists. RomM 5.0.0's GET /api/roms/{id}/notes fails serialization (UserNoteSchema validation in endpoints/roms/notes.py) whenever the ROM has at least one note. Creating and deleting notes work; romm_rom_notes (and the read-back after romm_add_note) will error until fixed upstream.

• Library scans can't be triggered over REST. RomM 5.0.0 flags scan_library as manual_run: false, so POST /api/tasks/run/scan_library is rejected. romm_scan_library reports this instead of failing; scans run on the configured schedule or from the web UI.

License

MIT. See CHANGELOG.md for release history.