Routara MCP Server
MCP serverMediaThis connects your AI to Routara, a service that provides text, image, and video generation through OpenAI-compatible APIs. Once added, your AI can chat with text models for writing and reasoning, create images from a description, and turn a short text prompt into a video clip.
Unavailable. This server has no hosted endpoint yet, so Ahel can't serve it.
Add to setup to save this item as a reference. Ahel cannot run it, and signing in will not install it.
What your AI can do with it
- List the models available in the Routara catalog
- Chat with text models for writing, coding help, and reasoning
- Generate images, illustrations, or posters from a text description
- Start a short video clip from a text prompt
- Check the status of a video task and see when it is ready
Getting started
- Save this item in Your setup as a reference.
- Read the source or reference documentation for its setup requirements. Saving it here does not connect it to your AI.
- Check this page for availability before trying to install it through Ahel.
From the project's README
As published by 36412749-collab/routara-mcp in README.md.
Official Model Context Protocol server for Routara. Use Routara chat, image, and video models from Cursor, Claude Desktop, Codex, Windsurf, VS Code, and other MCP clients.
- Website and setup guide: https://routara.ai/mcp?utm_source=github&utm_medium=repository&utm_campaign=mcp_quickstart
- OpenAI-compatible API: https://api.routara.ai/v1
- Create an API key: https://routara.ai/auth?mode=register&returnTo=%2Fapp&utm_source=github&utm_medium=repository&utm_campaign=mcp_quickstart
- Run a first OpenAI SDK request: Python and Node.js quickstart
- Try the API in Postman: importable first-request collection
Install
npx -y routara-mcp
Or install the one-click routara-mcp.mcpb bundle from the latest GitHub release.
Tools
| Tool | Description |
|---|---|
routara_list_models | Search and paginate the live model catalog |
routara_chat | Single-turn or multi-turn chat, including tool calls |
routara_generate_image | Text-to-image and reference-image generation |
routara_generate_video | Text-to-video and image-to-video submission |
routara_get_video_status | Poll an asynchronous video task |
MCP client configuration
{
"mcpServers": {
"routara": {
"command": "npx",
"args": ["-y", "routara-mcp"],
"env": {
"ROUTARA_API_KEY": "sk-or-v1-YOUR_KEY_HERE"
}
}
}
}
OpenAI Codex
[mcp_servers.routara]
command = "npx"
args = ["-y", "routara-mcp"]
enabled = true
[mcp_servers.routara.env]
ROUTARA_API_KEY = "sk-or-v1-YOUR_KEY_HERE"
After adding the config, restart your MCP client and ask it to list Routara models. Then ask it to use routara_chat with a model available to your account. The MCP connection exposes tools; it does not replace the host application's own model subscription or billing.
Environment
| Variable | Required | Default |
|---|---|---|
ROUTARA_API_KEY | Yes for tool calls | None |
ROUTARA_API_BASE | No | https://api.routara.ai/v1 |
ROUTARA_API_TIMEOUT_MS | No | 30000 |
The process can start and complete the MCP handshake without an API key. A key is resolved only when a Routara tool is invoked, which lets directories validate the server safely.
Reliability and compatibility
- Requests time out instead of hanging indefinitely.
- Transient network errors, HTTP 429, and HTTP 5xx responses are retried with bounded backoff.
- API errors include the upstream request ID and retry delay when available.
routara_chatreturns the complete OpenAI-compatible response, preserving reasoning content and tool calls.- Media parameters are forwarded only when explicitly supplied; model-specific support varies.
Development
npm ci
npm run build
npm test
npm run validate:registry
npm run build:mcpb
For a live API smoke test:
ROUTARA_API_KEY=sk-or-v1-... npm run test:live
Directory listings
Security
Do not commit API keys. If a key is exposed, revoke it in the Routara dashboard immediately. Please report security issues privately to support@routara.ai.
License
MIT
Tools it gives your AI (5)
| Tool | What it does |
|---|---|
| routara_list_models | List Routara catalog models (OpenAI-compatible GET /v1/models). WHEN TO USE: Discover model slugs before calling routara_chat, routara_generate_image, or routara_generate_video. |
| routara_chat | Chat completion via Routara (OpenAI POST /v1/chat/completions). WHEN TO USE: Text generation, coding help, reasoning, translation, or any LLM chat task. |
| routara_generate_image | Generate an image via Routara (POST /v1/images/generations). WHEN TO USE: User asks for image, illustration, poster, or visual asset from a text prompt. WHEN NOT TO USE: Video... |
| routara_generate_video | Submit async video generation (POST /v1/videos/generations). WHEN TO USE: User wants a short video clip from a text prompt. |
| routara_get_video_status | Poll async video task status (GET /v1/videos/:id). WHEN TO USE: After routara_generate_video returns a task id. |
Signals
- GitHub stars
- 1
- Last commit
- Oct 2026
- Weekly downloads
- 48
- Tools captured
- 5
Advanced
- Delivery
- routara-mcp MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-36412749-collab-routara-mcp- Source
- github.com/36412749-collab/routara-mcp
github.com/36412749-collab/routara-mcp