Skip to main content
Use Make’s MCP Client app in a scenario. Start with a direct tool call before adding an AI task. Make currently labels this app Open Beta; account features and pricing can change.

​
1. Try the sandbox

  1. Add MCP Client → Call a tool to a scenario and create a connection.
  2. Choose + New MCP Server and enter https://plainrouter.com/mcp/sandbox.
  3. Leave API Key / Access token empty and save.
  4. Select get_account_state, supply no arguments, and run that module. Check for sandbox: true.
For an AI-led check, use Execute an action with AI, select the sandbox tools, configure its AI provider and use the prompt below. AI usage follows your Make or provider billing. The sandbox needs no Plainrouter account or key, returns synthetic data, and never contacts Meta. Ask:
Both calls should succeed and include sandbox: true. This checks the connection, not production data or ad execution.

​
2. Create a workspace key

In Plainrouter, select your workspace and open Settings → Workspace keys. Create a Read key for analysis; use Write for Actions, including Actions record reads. Copy it once into your protected credential configuration. Each key covers one workspace. Never put keys in prompts or source control. Key permissions and replacement.

​
3. Add Plainrouter to the client

Create a separate MCP Client connection:
  1. Choose + New MCP Server with URL https://plainrouter.com/mcp.
  2. Enter your Workspace key in API Key / Access token, then save. Plainrouter expects the credential as a bearer token.
  3. If the connection instead starts OAuth, complete Plainrouter sign-in and choose the account and access tier.
  4. Use Call a tool → get_install_instructions without arguments for the first production check. For AI tasks, use Execute an action with AI and initially expose only that tool.
Keep credentials in the saved connection, not scenario text or the AI task prompt.

​
4. Verify the connection

Start with this read-only request:
Check the tool result, not just the assistant’s summary: the workspace must be yours and the call must succeed. This workspace-only read works before connecting Meta. For account diagnostics, connect Meta and verify the selected account. Agent replies can vary. In Ask, changes wait for approval; in Full, policy-allowed changes run automatically. Rule violations are blocked in either mode. A client’s tool confirmation is separate from Plainrouter’s execution controls.

​
Send conversions from a workflow

Conversion sending uses a separate HTTP request to POST https://plainrouter.com/api/v1/events, authenticated with a Server secret, not an MCP Workspace key. Map the Conversion API body from a real eligible website event. Preserve its event ID and original time on retries, and supply the required consent and visitor context. Start with the automation solution and synthetic n8n exercise. A sandbox result does not verify production event delivery or attribution. Verify HTTP event acceptance and Meta delivery separately from the MCP connection.

​
5. Troubleshooting

  • Wrong MCP app: use MCP Client to call Plainrouter. Make’s own MCP server exposes Make scenarios to other clients.
  • 401 on a tool call: check the saved credential and selected connection; the sandbox needs none, production requires workspace authorization.
  • AI task does not call a tool: try Call a tool first, then check selected tools and AI provider access. A module’s accepted configuration is not a completed tool call.
Reference: Make MCP Client connection and module reference. Choose another client.