Doroseek
@junjiepro
About Doroseek
Access all your OpenAI Compatible endpoints with the same base URL and API key.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"doroseek": {
"command": "deno",
"args": [
"task",
"start"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Doroseek?
Doroseek is a multi-purpose AI app built with Deno and Fresh that provides OpenAI-compatible endpoints, an MCP server with built-in tools, and an MCP proxy server to connect to other MCP servers. It is designed for developers who want to aggregate multiple AI endpoints and use MCP tools via SSE.
How to use Doroseek?
Install Deno, copy .env.example to .env, set ADMIN_KEY and MCP_MAX_DURATION environment variables, optionally configure the database, then run deno task start from the root of the repository. Access OpenAI-compatible routes via /{key} or /api, MCP SSE via /mcp/{server}/sse, and MCP proxy via /mcp/proxy/sse with appropriate parameters.
Key features of Doroseek
- OpenAI Compatible endpoints with key management and alias assignment
- Built-in MCP servers: Sequential Thinking and Think Tool
- MCP Proxy server to connect to stdio or SSE MCP servers
- Route-based access control with API keys
- Local development with Deno and Fresh framework
- Configurable maximum SSE connection duration
Use cases of Doroseek
- Aggregate multiple OpenAI-compatible endpoints under one base URL and API key
- Use MCP tools like Sequential Thinking via SSE from any MCP client
- Proxy connections to external MCP servers (stdio or SSE) for centralized management
- Share restricted access to AI endpoints with others using generated Doroseek API keys
FAQ from Doroseek
What is the difference between Doroseek and a direct OpenAI endpoint?
Doroseek allows you to manage multiple endpoints, assign aliases, and generate API keys for shared access, while also providing MCP server capabilities.
What are the runtime requirements?
Doroseek requires Deno to run locally and uses Deno's OpenKv for database by default.
Where does data live?
Data is stored locally in a Deno OpenKv database, defaulting to a local file (./db). No external database is required by default.
What transports are supported for MCP?
Doroseek uses SSE transport for its MCP SSE server and MCP Proxy server. The proxy can connect to stdio or external SSE servers.
How do I restrict access to my endpoints?
Set the ADMIN_KEY environment variable to restrict creation of settings to only that key; otherwise, any key can create its own settings.
More Other MCP servers

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Comments