A side-by-side look at the Openrouter MCP Multimodal and Tanvo MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Openrouter MCP Multimodal for multimedia process work as a local process; choose Tanvo for multimedia process as a local process. You can also run both side by side in one mcpServers block.
OPENROUTER_API_KEY.chat_completion, start_chat_completion, get_chat_completion_status.find_apps, get_app, generate_from_app.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 68/100 · Great | 56/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | Not declared |
| Pricing | BYOK (pay the provider) | Not declared |
| Required env vars | OPENROUTER_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 99 | 0 |
| Directory activity | 6 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 21 | 10 |
| Full listing | View Openrouter MCP Multimodal | View Tanvo |
chat_completionText chat, web search, provider routing, caching, reasoning, structured outputstart_chat_completionAsync background job for long-running reasoning modelsget_chat_completion_statusPoll / retrieve async completion resultsanalyze_imageVision — local path, URL, or data URL + `questionanalyze_audioTranscribe / analyze audio filesanalyze_videoDescribe / Q&A over video filesgenerate_imageText-to-image via chat completions with reference imagesgenerate_image_dedicatedText-to-image via dedicated `/api/v1/images` (resolution, quality, format)generate_audioText-to-speech / music via chat completionstext_to_speechDedicated TTS (`/api/v1/audio/speech`) — Deepgram, ElevenLabs, OpenAI; voices, speed, mp3/pcmspeech_to_textDedicated STT (`/api/v1/audio/transcriptions`) — Whisper, GPT-4o Transcribe, Voxtral, ElevenLabs Scribegenerate_videoText-to-video (async, resumable)find_appsSearch the apps by what the user wants ("royal pet portrait", "fix an old photo")get_appAn app's inputs and looks, with example outputs, prompts and costgenerate_from_appRun an app's look on the user's photosgenerate_imageText to image, or edit / combine photosgenerate_videoText or image to video (returns an id; videos take minutes)generate_musicWrite a song: describe it, bring lyrics, or go instrumentalget_generationStatus and outputs of a run; can wait and save fileslist_modelsEvery model, its options and its credit costaccountFree tier or account, and the credits leftopen_in_tanvoA link that opens the app, look or studio ready to goPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"stabgan-openrouter-mcp-multimodal": {
"command": "npx",
"args": [
"-y",
"@stabgan/openrouter-mcp-multimodal"
],
"env": {
"OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"tanvo": {
"command": "npx",
"args": [
"-y",
"tanvo-mcp"
]
}
}
}