13 FOCUSED GUIDES

MCP & agent workflows

Connect an agent, diagnose tool access and make backend changes against the project that actually exists.

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.

Generate an MCP configuration
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.

Read the guide →
PRACTICAL FIELD GUIDE

Streamable HTTP or stdio for MCPBackend?

MCPBackend is a hosted Streamable HTTP MCP service, so the client connects to a URL rather than launching a local server process.

Read the guide →
PRACTICAL FIELD GUIDE

MCP connects, but backend tools are not visible

A connection indicator does not prove that tool discovery completed or that the client enabled the returned tools.

Read the guide →
PRACTICAL FIELD GUIDE

MCP OAuth keeps returning to consent

A repeated consent flow can indicate a mismatch between the client's registered callback, stored connection state or selected account.

Read the guide →
PRACTICAL FIELD GUIDE

MCP returns unauthorized after a successful connection

An MCP authorization error concerns the agent's account connection, not automatically your app's API key or end-user login.

Read the guide →
PRACTICAL FIELD GUIDE

Your agent is changing the wrong project

Project identity needs to be explicit before a coding agent makes backend changes.

Read the guide →
PRACTICAL FIELD GUIDE

Have an agent inspect the schema before creating tables

An existing backend should be inspected before an agent creates new tables or columns.

Read the guide →
PRACTICAL FIELD GUIDE

Use get_project_api instead of guessing REST routes

The generated project contract is the source for the routes and schema an agent should use.

Read the guide →
PRACTICAL FIELD GUIDE

Verify an agent's backend change after the tool returns

A successful tool response is one part of verification, not proof that the full feature works.

Read the guide →
PRACTICAL FIELD GUIDE

Agent Skill versus MCP server: what each contributes

An Agent Skill provides workflow instructions, while the MCP server supplies authenticated tools.

Read the guide →
PRACTICAL FIELD GUIDE

An MCP mutation timed out: inspect before retrying

A timed-out tool call may have completed on the server even if the client did not receive its response.

Read the guide →
PRACTICAL FIELD GUIDE

An agent created an API key: handle the one-time secret

Creating an API key returns sensitive material that should be stored for the intended server integration.

Read the guide →
PRACTICAL FIELD GUIDE

Limit an agent workflow to the intended team projects

An agent's useful reach depends on the connected account's project permissions.

Read the guide →