# LobeHub

LobeChat and LobeHub Cloud read remote MCP servers from the MCP Marketplace settings. Add Cakewalk's gateway as an HTTP server with OAuth 2.0 and the tools become available to your chats.

## Install Method

Custom form in LobeChat's MCP Marketplace. Add Cakewalk as an HTTP MCP server with OAuth 2.0 authentication. LobeChat verifies the server is reachable and authentication works before tools become available.

## Step 1: Open the MCP Marketplace

1. Open LobeChat or LobeHub.
2. Open MCP Marketplace settings.

## Step 2: Add the Cakewalk Gateway

1. Add a custom MCP server.
2. Set the type to **http**.
3. Enter the URL: `https://mcp-gateway.getcakewalk.io/mcp`.
4. Set authentication to **OAuth 2.0**.

## Step 3: Authenticate

LobeChat starts the OAuth flow with Cakewalk's gateway. Sign in with your Cakewalk account and approve the Connection. LobeChat stores the resulting access token.

## Verifying It Works

LobeChat verifies the server is reachable and authentication works. After verification, the available tools appear under the server entry. In Cakewalk, the LobeHub card on **My Agents** flips to **Connected** after the first agent call.

## Troubleshooting

* **OAuth flow returns to an error page:** copy the full callback URL from your browser's address bar and paste it back into LobeChat. LobeChat treats the callback URL as the trigger to exchange code for token.
* **Server verification fails:** confirm the URL is exact and that `mcp-gateway.getcakewalk.io` is reachable from LobeChat's runtime. For self-hosted LobeChat, confirm outbound traffic to the gateway is allowed.

## Learn more

* [MCP Marketplace](https://lobehub.com/docs/usage/community/mcp-market) from LobeHub.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://www.cakewalk.security/docs/ai-agent-access/connections-and-integrations/agent-platforms/lobehub.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.