Back to Blog
Make Issues

[Make New Feature] Make MCP Client

Make MCP Client Feature Expansion

2025.07.17
[Make New Feature] Make MCP Client

MAKE Issue: Make MCP Client Feature Expansion

Graphic showing interaction between Make MCP client and server, displaying client and server functions together.

AI agents are excellent at thinking, but to truly leverage them, they need to be connected to good tools.

AI Agent Builder provides tools to visually create agent workflows, helping teams and creators think and automate actions in one place.

Next, we introduced the Make MCP (Model Context Protocol) Server.

This server made it easy and secure to use Make scenarios as tools from external models like Claude or GPT.

Now Make is expanding its capabilities further with the MCP Client.

With this new module, Make scenarios or agents can securely and visually use tools hosted outside of Make, without writing complex code, installing local servers, or building external infrastructure.

Let's explore what this module means and how you can start using it right away.

https://youtu.be/RgHYL3hV5p4

What Is Make MCP?

MCP stands for Model Context Protocol, a method that allows AI agents to communicate easily and securely with real-world tool workflows.

Whether these tools are inside or outside Make, MCP creates a standard for tool connectivity.

This enables agents to move beyond simply generating ideas to taking reliable, real-world actions.

MCP Server - Exposes Make scenarios as tools to the outside world.

MCP Client - Connects to tools hosted on external MCP servers.

When used together, agents can work across multiple systems with complete control and clear structure, without any custom code.

What Is Make MCP Server?

The Make MCP Server lets you turn scenarios into tools that AI agents can call when needed.

Select the scenarios you want to expose, create a secure URL and token, then share them with the model you're using, like Claude or GPT.

That model can then execute scenarios with structured inputs and receive structured outputs.

https://youtu.be/M9jpyB-15VY

No server to run. No API to build. Just secure, token-based access to the automations you're already using.

When to use it:

  • When you want to run scenario builder capabilities from external models
  • When building agent systems that rely on structured actions
  • When you need a fast, reliable way to expose workflows as callable tools

What Is Make MCP Client?

The Make MCP Client lets you call tools hosted on remote MCP servers like GitHub, Webflow, PayPal, and more from your scenarios.

Add the module to your scenario, enter the server URL, and Make automatically loads the available tools.

Then visually connect inputs with help text and schema validation, and execute securely using OAuth or token-based authentication.

It's a clean, visual way to extend your automations to tools outside Make without local server installs or complex API calls.

When to use it:

  • When your scenarios or AI agents need access to tools not available in Make
  • When you want to connect to partner-hosted or internal AI capabilities
  • When you need a scalable but code-free way to execute external actions

Why Use MCP Client?

The MCP Client is built for teams that want to move fast without giving up structure, security, or control.

It eliminates the hassle of building custom integrations or running local infrastructure.

Instead of setting up servers or writing HTTP requests by hand, you just add the module, connect, and configure everything visually.

No hosting required - Connect to external tools without running your own servers

No code needed - Use Make's visual UI to connect fields and set inputs

Secure by design - Supports OAuth and securely connects user inputs

Flexibility - Works with AI agents or regular scenarios

Whether you're expanding the scope of your AI agents or unifying tools across teams, the MCP Client lets you work faster and smarter.

How MCP Client Works

Using the MCP Client is simple but powerful.

Add the module - Place the MCP Client module in your scenario.

Enter the server URL - Point to an MCP-compatible server (e.g., Asana, Paypal, Webflow, Github).

Select a tool - Choose from the list of available tools provided by the server.

Connect inputs - Configure your request using fields and help text that appear automatically.

Execute - Let the AI agent (or scenario) run the tool and act on the response.

Everything happens inside the scenario builder, with no tool switching, copy-pasting, or guesswork.

MCP Client and Server - Better Together

The MCP Client and Server are designed to work together, so you don't have to choose one or the other.

  • Use MCP Server to expose Make scenarios as tools that external agents (like Claude or GPT) can call.
  • Use MCP Client to let your scenarios call tools hosted outside of Make.

Use both together for complete agent orchestration.

Using both together creates a bidirectional channel between the tools your automations and AI agents need to succeed.

One handles outgoing, the other handles incoming. You decide where the work happens.

Real-World Examples

The MCP Client provides new ways to automate across multiple platforms without writing custom code or managing infrastructure.

[Real-world examples]

  • A Claude agent fetches customer summaries from tools hosted on a LangChain server, then logs the results in a CRM through Make.
  • A product team combines both modules: using MCP Client to call a hosted summarization tool, and MCP Server to return results to the agent.
  • An operations team consolidates multiple MCP endpoints into a single Make-hosted MCP server, streamlining credentials, access, and agent exposure.
  • A support agent runs internal NLP pipelines using Make as a secure intermediary, without exposing underlying tools to external models.

Every use case is different, but the goal is the same: making automation more intelligent, flexible, and connected.

A Solution for Automation Teams Working Across Tech Stacks

The MCP Client isn't just about connecting to more tools — it's about reimagining what's possible with agentic automation.

On other platforms, integrating AI with real systems often hits walls: limited app libraries, inflexible HTTP workarounds, or the need to manage your own infrastructure.

With the MCP Client, Make offers a new model:

Dynamic connections to tools beyond Make's 2,000+ apps

Visual orchestration across internal and external systems

A single canvas where AI agents, APIs, and automations all work together

Use the tools you already know while building faster, smarter, connected intelligent systems.

Getting Started with MCP Client

The MCP Client is currently available on all paid plans and can be set up in minutes.

Add the module to your scenario, connect to a remote MCP server, and configure tools visually.

No hosting needed. No custom APIs. Just more ways to make your automation more efficient.

Source: Patrik Simek, Make, "Make MCP Client: Connect your scenarios to external tools", https://www.make.com/en/blog/mcp-client, (2025. 7. 16)

Interested in AI automation?

Find the right solution for your business through a free consultation.

Get a Free Consultation