PRACTICAL FIELD GUIDE
Which MCPBackend endpoint should your agent connect to?
The coding agent connects to the remote MCP endpoint, while the application connects to the data API. Mixing those addresses produces confusing errors before any database work begins.
MCPBackend editorial team · · Examples are illustrative
Put it into practice
- Use https://mcp.mcpbackend.com/mcp for the remote MCP connection and select a compatible HTTP transport.
- Complete the client's supported OAuth flow under the intended developer account.
- List projects and inspect the chosen project's API contract before generating app requests.
What this looks like
ILLUSTRATIVE EXAMPLE
An agent is configured with the marketing homepage. It receives HTML instead of an MCP initialization response even though the website loads correctly.
A boundary to keep clear
Do not substitute the data API hostname for the MCP endpoint. They accept different protocols and credentials.
MCPBackend context
MCPBackend's remote MCP server manages supported project configuration through your authorized account. Your running app uses the separate data API. A successful connection does not prove every tool call succeeded: inspect tool results, verify the project identity and read the current schema before a change.
Take the next step
Inspect the current project contract, try the change with disposable data, and verify the result through the same credentials your app will use. Record the expected response and one denied-access case before release.
Sources and further reading
These references explain the underlying protocols and design principles. For supported MCPBackend operations and exact request shapes, inspect your project’s generated API contract.