OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).
Routara MCP Server (io.github.36412749-collab/routara-mcp)
This Model Context Protocol (MCP) server is an OpenAI-compatible integration for Routara, providing access to chat, image, and video APIs via api.routara.ai. It is described as an official MCP server for Routara models and supports use from MCP-capable clients.
🛠️ Key Features
OpenAI-compatible LLM, image, and video APIs via Routara (api.routara.ai)
Uses Model Context Protocol (MCP)
Distributed as routara-mcp (npm package listing referenced)
🚀 Use Cases
Access Routara chat models through MCP clients such as Cursor and Claude Desktop
Use image and video models from tools including Codex, Windsurf, and VS Code
⚡ Developer Benefits
Targets MCP tooling and clients that support Model Context Protocol
OpenAI-compatible API behavior for LLM requests
⚠️ Limitations
Source material only specifies integration scope (chat/image/video) and compatibility; no additional capabilities, configuration, or tooling details are provided.
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.
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_chat returns the complete OpenAI-compatible response, preserving reasoning content and tool calls.
Media parameters are forwarded only when explicitly supplied; model-specific support varies.
Development
bash
npm ci
npm run build
npm test
npm run validate:registry
npm run build:mcpb
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
Install
Configuration
Environment variables
ROUTARA_API_KEYrequiredsecret
Routara API key (sk-or-v1-...) from https://routara.ai/#auth
ROUTARA_API_BASE
Optional API base URL (default https://api.routara.ai/v1)
