Provides an MCP server that exposes Make scenarios as AI-ready tools with lifecycle management.
Configuration
View docs{
"mcpServers": {
"forayconsulting-make_mcp": {
"command": "node",
"args": [
"/path/to/make-mcp-server/build/index.js"
],
"env": {
"MAKE_TEAM": "<your-team-id>",
"MAKE_ZONE": "<your-zone>",
"MAKE_API_KEY": "<your-api-key>"
}
}
}
}You can run and manage Make Context Protocol (MCP) servers that expose Make scenarios as tools for AI assistants. This fork extends the base MCP server with full scenario lifecycle management, letting you list, create, modify, activate, run, and observe scenarios while integrating securely with your Make.com workflows.
You will interact with the MCP server through your preferred MCP client. The server exposes tooling to run on-demand scenarios, inspect and manage scenarios, view execution logs, and configure scenario interfaces. Use the provided tools to trigger scenarios with the appropriate inputs, inspect results, and manage the lifecycle of your scenarios (create, update, clone, activate, deactivate, and delete). To get started, install the server components, configure your client with the required API keys and zone, then connect your AI assistant to call the available tools like run_scenario_{id}, list_scenarios, get_scenario, and get_logs.
Key capabilities include the ability to:
- Trigger on-demand Make scenarios via run_scenario_{id} and receive structured outputs
- List and view scenarios with status, details, and scheduling
- Create, clone, update, and delete scenarios, including blueprint management and interface configuration
- Activate or deactivate scenarios to control scheduled execution
- Retrieve incomplete execution logs for debugging and DLQ insights.Prerequisites are Node.js and access to your MCP client. You will configure MCP server connections in your client using either a local (stdio) runtime or a npx-based approach, as shown below.
{
"mcpServers": {
"make": {
"command": "node",
"args": ["/path/to/make-mcp-server/build/index.js"],
"env": {
"MAKE_API_KEY": "<your-api-key>",
"MAKE_ZONE": "<your-zone>",
"MAKE_TEAM": "<your-team-id>"
}
}
}
}{
"mcpServers": {
"make": {
"command": "npx",
"args": ["-y", "@makehq/mcp-server"],
"env": {
"MAKE_API_KEY": "<your-api-key>",
"MAKE_ZONE": "<your-zone>",
"MAKE_TEAM": "<your-team-id>"
}
}
}
}Configure the following environment variables in your client or deployment environment where the MCP server runs. The API key grants access to Make scenarios, and the zone and team identify your Make organization.
Environment variables to configure: - MAKE_API_KEY: Your Make API key with appropriate scopes - MAKE_ZONE: Your organization’s zone (for example, us2.make.com or eu1.make.com) - MAKE_TEAM: Your team identifier, typically found in your team URL
Treat API keys as sensitive credentials. Use least-privilege scopes where possible, and rotate keys periodically. When running locally or in a team environment, ensure access to the MCP client and server is restricted to authorized users only.
If you encounter connectivity or authorization issues, verify that your MAKE_API_KEY, MAKE_ZONE, and MAKE_TEAM values are correct and that the MCP server process has access to those environment variables. Check that the server process is running and that your MCP client points to the correct local runtime or MCP URL as configured.
Common workflows include listing scenarios to confirm available options, retrieving a scenario’s details before invoking it, then running a specific on-demand scenario with the required input parameters. Use get_logs to inspect incomplete executions if a run does not complete as expected.
This fork adds full scenario lifecycle management to the base MCP server. Planned future work includes further connection management, data store operations, and webhook configuration.
License information is defined in the upstream project and should be consulted for usage terms and restrictions.
Execute an on-demand scenario by its identifier with the required input parameters and receive structured results suitable for AI consumption.
List all scenarios with optional filtering by type or status to understand what is available.
Retrieve full details of a specific scenario, including its status and scheduling.
Create a new scenario, optionally with blueprint and scheduling definitions.
Update an existing scenario’s name, folder, blueprint, or scheduling.
Permanently delete a scenario.
Create a copy of an existing scenario for reuse or modification.
Fetch the blueprint for a scenario, including module flow and configuration.
Update the scenario blueprint to modify its module flow.
Define input parameters for on-demand scenarios to shape how AI assistants interact with them.
Retrieve incomplete execution logs (DLQ) for debugging.
Activate a scenario to enable scheduled executions.
Deactivate a scenario to pause scheduled executions.