Rostro
- Updated August 30, 2025
- francis-ros/rostro-mcp-server
Rostro is a MCP server that lets agents generate images, voice, video, 3D models, and music via a remote multimodal HTTP endpoint.
About
Rostro is a hosted Model Context Protocol server that extends large language model agents with multimodal generation capabilities. Through the remote endpoint at proto.rostro.dev, developers using Claude Code, Cursor, or other MCP-aware clients can request images, voices, videos, three-dimensional models, and music from within the same conversation that plans code and copy. makers adopt it when a prototype, demo, or content sprint needs assets immediately and they prefer a single MCP integration over juggling separate vendor dashboards. The registry lists version 1.0.0 with streamable-http transport and points to the rostro-mcp-server repository. It sits in the build-and-integrate lane of the journey but naturally supports grow and launch content work once wired. Expect dependency on Rostro’s hosted service and whatever account or usage terms apply on rostro.dev—not a self-hosted media pipeline.
- Remote streamable-http MCP endpoint at https://proto.rostro.dev/mcp (registry version 1.0.0).
- Exposes multimodal generation: images, voices, videos, 3D models, and music from LLM tool calls.
- Publisher metadata references cloud-deployer tooling (registry extension version 2.4.0 in _meta).
- GitHub source: francis-ros/rostro-mcp-server for implementation reference.
- Turns text-centric agents into producers of media assets without bespoke per-model SDK wiring.
Rostro by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http rostro https://proto.rostro.dev/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | None |
| Last updated | August 30, 2025 |
| Repository | francis-ros/rostro-mcp-server ↗ |
What it does
Let a text-only coding agent call Rostro over MCP to generate images, voice, video, 3D, and music for prototypes, demos, and marketing assets.
Who is it for?
Best when you're prototyping multimodal products, demo reels, or marketing creatives from an MCP-first agent setup.
Skip if: Skip if you need on-prem media generation, fine-grained model control without a hosted dependency, or pure codebase intelligence workflows.
What you get
After registering the proto.rostro.dev remote MCP, your agent invokes generation tools for media alongside coding and planning tasks.
- Agent-callable tools for images, voices, videos, 3D models, and music
- Unified multimodal surface inside MCP sessions
- Faster prototype and content asset iteration from agent chats
By the numbers
- Registry server version 1.0.0
- Remote MCP URL: https://proto.rostro.dev/mcp (streamable-http)
- Repository: github.com/francis-ros/rostro-mcp-server
README.md
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:
"rostro": {
"url": "https://proto.rostro.dev/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
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:
claude mcp add rostro -t http https://proto.rostro.dev/mcp
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.
Recommended MCP Servers
0Latency MemoryPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient Mcp1k patient MCP server
1trippulse1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.89How it compares
Remote multimodal generation MCP—not a repo graph tool like Repowise and not a payments oracle.
FAQ
Who is dev.rostro/rostro for?
Developers and agent users who want one MCP connection to generate images, audio, video, 3D, and music from LLM workflows.
When should I use dev.rostro/rostro?
Use it during build or content sprints when your agent must produce media assets without manual hops to separate creative tools.
How do I add dev.rostro/rostro to my agent?
Add the streamable-http remote MCP URL https://proto.rostro.dev/mcp in your client’s MCP config and follow Rostro account or auth steps required by the service.