Wire it up your way
Auto-setup covers most clients. For VS Code, Claude Desktop, or project-only configs ... here's every way to connect. The launch command is always the same:
$ npx --yes omni-vision-pro@latest serve
$ codex mcp add omni-vision-pro -- npx --yes omni-vision-pro@latest serve
Or add this to ~/.codex/config.toml (or .codex/config.toml in a trusted project):
[mcp_servers.omni-vision-pro]
command = "npx"
args = ["--yes", "omni-vision-pro@latest", "serve"]
startup_timeout_sec = 120
tool_timeout_sec = 1200
enabled = true
Restart or start a new session, then check /mcp.
Add to a project opencode.json / opencode.jsonc, or ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"omni-vision-pro": {
"type": "local",
"command": ["npx", "--yes", "omni-vision-pro@latest", "serve"],
"enabled": true,
"timeout": 600000
}
}
}
On Windows, ~ means your user folder. Restart OpenCode and run opencode mcp list.
$ claude mcp add --scope user --transport stdio omni-vision-pro -- npx --yes omni-vision-pro@latest serve
Project scope from the project root (entries live in .mcp.json):
$ claude mcp add --scope project --transport stdio omni-vision-pro -- npx --yes omni-vision-pro@latest serve
Verify with claude mcp list.
Put this in ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):
{
"mcpServers": {
"omni-vision-pro": {
"type": "stdio",
"command": "npx",
"args": ["--yes", "omni-vision-pro@latest", "serve"]
}
}
}
Reload the window, then open Settings > Tools & MCP and enable the server if needed.
.vscode/mcp.json:{
"servers": {
"omni-vision-pro": {
"type": "stdio",
"command": "npx",
"args": ["--yes", "omni-vision-pro@latest", "serve"]
}
}
}
Start it from the inline action, run MCP: List Servers, and approve the trust prompt.
claude_desktop_config.json:{
"mcpServers": {
"omni-vision-pro": {
"command": "npx",
"args": ["--yes", "omni-vision-pro@latest", "serve"]
}
}
}
Windows: %APPDATA%\Claude\claude_desktop_config.json · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json. Completely quit & reopen Claude Desktop after saving.
Troubleshooting
Stuck? Here's the fix
Clipboard import cannot find the key
Copy only the Gemini/OpenAI key, then run provider set --from-clipboard again.
A key was added but OCR is still active
Run provider status, then provider on, and restart/reload the AI client.
The wrong AI provider is being used
Run provider, choose the provider you want, then restart/reload the AI client.
The client cannot find npx
Install Node.js 20.10+, restart the client, or replace npx with its full path such as C:\Program Files\nodejs\npx.cmd.
The server is installed but not visible
Run doctor, restart/reload the client, then approve the server or project trust prompt.
An image attachment is not found
Attach the image in the same request, or pass its inline data URL. No special copy folder is needed.
OCR takes too long
The first OCR request starts a local worker. Keep client tool timeouts above 90 seconds; image arrays run sequentially.
Gemini reports a retired model
Set GEMINI_MODEL=gemini-2.5-flash in the private .env.
Code or ZIP access is denied
If OMNI_ALLOWED_ROOTS is set, include the intended project folder, restart the client, and try again.
A config entry looks wrong
Setup preserves unrelated settings and creates backups before changing JSON/JSONC client files.
Skip the manual work ... one command
Let the installer detect, configure and verify everything for you.