Make MCP server allows external AI systems, such as AI agents, to run your scenarios and manage the contents of your Make account. Model Context Protocol (MCP) is a communication standard between AI systems and external systems. It enables them to easily and safely interact by defining endpoints and providing authentication.
Benefits
Creates bidirectional communication between AI and Make
Allows AI to access and manage elements of your Make account
Turns your active and on-demand scenarios into callable tools for AI
Make MCP server gives external AI systems access to scenario run and management tools that enable the following capabilities:
Run active and on-demand scenarios
View and modify scenarios and their related entities (e.g., connections, webhooks, and data stores)
View and modify teams and organizations
When connecting Make MCP server to an AI system, you select the scopes to determine the tools available to the system.
When connecting to Make MCP server, note that the use of scenarios as tools is available to all plans, and management tools are available to paid plans.
Inputs and outputs
If you're using scenarios as tools, you can help AI understand what data to receive and send by configuring scenario inputs and outputs:
Inputs: parameters your AI fills with data when the scenario runs
Outputs: data returned from the scenario to your AI
Make MCP server is a cloud-based server hosted by Make, running via Server-Sent Events (SSE) and Streamable HTTP.
If your MCP client supports SSE, use the following connection URLs, depending on your connection type:
If your MCP client does not support SSE, use the Cloudflare mcp-remote proxy for compatibility. Refer to Cloudflare's MCP Remote Proxy Guide for more details.
If your MCP client supports Streamable HTTP, use /stream instead of /sse at the end of the connection URL specified for your chosen connection type (OAuth or MCP token).