Remote proxy for Model Context Protocol, allowing local-only clients to connect to remote servers using oAuth
Remote proxy for Model Context Protocol, allowing local-only clients to connect to remote servers using oAuth
Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server, with auth support:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"remote-example": {
"command": "npx",
"args": [
"mcp-remote",
"https://remote.mcp.server/sse"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AUTH_TOKEN | Credential the server authenticates with. | Yes |
| AUTH_HEADER | Configuration value read at startup. | Optional |
| HTTPS_PROXY | Configuration value read at startup. | Optional |
| NO_PROXY | Configuration value read at startup. | Optional |
| NODE_EXTRA_CA_CERTS | Configuration value read at startup. | Optional |
| MCP_REMOTE_CLIENT_ID | Configuration value read at startup. | Optional |
| MCP_REMOTE_CLIENT_SECRET | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Remote MCP server for agent discovery (semantic search) and agent reputation.
Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery
이 프로젝트는 [채널톡](https://api-doc.channel.io/) 의 OPEN API를 활용하여 Model Context Protocol(MCP)과 연동하는 도구입니다. 이를 통해 AI 어시스턴트가 채널톡의 채팅 정보에 접근하고 활용할 수 있습니다.
Pull requests to this repository are welcome.