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](https://rostro.dev/login/sign_up) 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](https://cursor.com/en/install-mcp?name=Rostro&config=eyJ1cmwiOiJodHRwczovL3Byb3RvLnJvc3Ryby5kZXYvbWNwIiwiaGVhZGVycyI6e319) - **LM Studio**: [Install in LM Studio](https://lmstudio.ai/install-mcp?name=rostro&config=eyJ1cmwiOiJodHRwczovL3Byb3RvLnJvc3Ryby5kZXYvbWNwIn0%3D) ## API Key Setup (Optional) For fixed API authentication instead of OAuth, add this to your settings: ```json "rostro": { "url": "https://proto.rostro.dev/mcp", "headers": { "Authorization": "Bearer <YOUR_API
Rostro Image, Video, 3D, Voice, SFX, Music is a remote MCP server published at mcp.rostro.dev. It has been probed 24 times since 9/10/2026. It answered in 24 of them (100.0%), a near-uninterrupted record. Median response time is 1,144 ms, a delay an agent will notice. Its tool list could not be read; the server is closed to direct calls. It answers direct calls with an authentication wall.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 01:33:33 | Auth-gated | 401 | 965 | 401 | 1144 | — |
| 2026-09-12 23:31:36 | Auth-gated | 401 | 1027 | 401 | 1039 | — |
| 2026-09-12 21:29:15 | Auth-gated | 401 | 865 | 401 | 878 | — |
| 2026-09-12 19:27:29 | Auth-gated | 401 | 1613 | 401 | 1664 | — |
| 2026-09-12 17:24:09 | Auth-gated | 401 | 1331 | 401 | 1343 | — |
| 2026-09-12 15:21:42 | Auth-gated | 401 | 958 | 401 | 977 | — |
| 2026-09-12 13:29:16 | Auth-gated | 401 | 1245 | 401 | 1245 | — |
| 2026-09-12 11:39:06 | Auth-gated | 401 | 1485 | 401 | 1491 | — |
| 2026-09-12 09:47:15 | Auth-gated | 401 | 1288 | 401 | 1230 | — |
| 2026-09-12 07:55:23 | Auth-gated | 401 | 1401 | 401 | 1373 | — |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/francis-ros-rostro-mcp)<a href="https://mcpmetrics.io/servers/francis-ros-rostro-mcp"><img src="https://mcpmetrics.io/badge/francis-ros/rostro-mcp/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
Provides UX capabilities to enhance the design output and understanding of AI systems.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Authentication-Info nextnonce shape, value discarded
Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
290+ quality-scored API capabilities for AI agents across 27 countries via MCP.
Fibre optics, OTDR, network design and data centre notes from SPLIDIA, plus its service catalogue.
Comments
Sign in to write a comment
No comments yet. Be the first.