
Rostro
dev.rostroPublished by rostro.devOfficial publisherv1.0.0Updated Oct 24, 2026
Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
Overview
Remote MCP server that lets an assistant generate images, music, videos, voices and 3D models, adding multimodal output to any language model.
- What you can do
- Generate images, videos and 3D models from prompts
- Generate music and voices
- Add multimodal generation to a model that lacks it natively
- Tools are built for language models with minimal context overhead
- When to use it
- Use it when you want an assistant to produce media assets — pictures, audio, music, video or 3D models — directly from a conversation, especially with a model that has no native generation capability.
- Requirements
- A remote MCP endpoint at A Rostro account is required for OAuth sign-in; alternatively a fixed API key can be supplied in an Authorization Bearer header. No local runtime or packages needed.
Installation
In SourceWeft
- Open Rostro in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/dev.rostro%2Frostro/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"rostro": {
"type": "http",
"url": "https://proto.rostro.dev/mcp"
}
}
}README
Rostro's MCP Server
Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.
Quick Setup
You will need a Rostro account for OAuth discovery and authentication in your client of choice.
MCP Server URL: https://proto.rostro.dev/mcp
Quick Install Links
- Cursor: Install in Cursor
- LM Studio: Install in LM Studio
API Key Setup (Optional)
For fixed API authentication instead of OAuth, add this to your settings:
Get an API key from your account page.
Client-Specific Setup
Claude Desktop and Claude.ai
- Go to Claude Connectors
- Click "Add Custom Connector"
- Fill out the form:
- Name: "Rostro"
- URL: "https://proto.rostro.dev/mcp"
- Click "Add"
- Hit "Connect" and follow the OAuth flow
- Optionally, click "Configure" to give Claude preapproval for individual tools
Claude Code
Install using the command line:
Then start Claude and follow the instructions to complete authentication.
What is MCP?
Model Context Protocol (MCP) is an open standard that allows language models to securely connect to third-party data sources and tools.
Source: README.md at commit 5eb7bcf
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts

