Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 58 Actions

Make MCP Server
for AI Agents

Connect your AI agent to StackOne's Make MCP server and give it 58 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Make logo
Make MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

58 Agent Actions

Create, read, update, and delete across Make — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Make MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Make tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Make call.

Tools Discovery →

What is the Make MCP Server?

A Make MCP server lets AI agents read and write Make data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Make MCP server ships with 58 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Make MCP Tools

Every action from Make's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

AI Agents

  • Create AI Agent

    Create a new AI agent.

  • List AI Agents

    Retrieve a list of all AI agents for a team.

  • Get AI Agent

    Retrieve an AI agent by its ID.

  • Update AI Agent

    Modify an existing AI agent by its ID.

  • Delete AI Agent

    Delete an AI agent by its ID.

Agents

  • Create Agent

    Create a new agent.

  • List Agents

    Retrieve a collection of agents for an organization.

  • Get Agent

    Retrieve agent details by ID.

  • Update Agent

    Update an agent's properties.

  • Delete Agent

    Remove an agent.

Connections

  • List Connections

    Retrieve a collection of all connections for a team.

  • Get Connection

    Retrieve details of a connection.

  • Delete Connection

    Delete a connection.

Data Structures

  • Create Data Structure

    Create a new data structure.

  • List Data Structures

    Retrieve a collection of all data structures for a team.

  • Delete Data Structure

    Delete a data structure.

Scenario Folders

  • Create Scenario Folder

    Create a new scenario folder.

  • List Scenario Folders

    Retrieve a collection of all scenario folders for a team.

Organizations

  • Create Organization

    Establish a new organization with specified configuration.

  • List Organizations

    Retrieve a collection of all organizations the user has membership in.

  • Get Organization

    Fetch comprehensive details about a specific organization.

  • Update Organization

    Modify organization name, timezone, or country settings.

  • Delete Organization

    Remove an organization and all associated teams.

Scenarios

  • Create Scenario

    Create a new scenario with data passed in the request body.

  • List Scenarios

    Retrieve a collection of all scenarios for a team or organization.

  • Get Scenario

    Retrieve all available properties of a scenario.

  • Update Scenario

    Update a scenario with a given ID by passing new values.

  • Delete Scenario

    Delete a scenario with a given ID.

Teams

  • List Teams

    Get the list of teams in an organization.

  • Get Team

    Returns information about a team.

Team LLM Configurations

  • Get Team LLM Configuration

    Retrieve the LLM configuration for a team.

  • Update Team LLM Configuration

    Update the LLM configuration for a team.

Users

  • List Users

    Retrieve a collection of users for a team or organization.

  • Update User

    Update user details.

User Team Roles

  • List User Team Roles

    Get team roles of a specific user.

  • Get User Team Role

    Get user role detail in a specific team.

  • Update User Team Role

    Update the user role in a team.

User Organization Roles

  • List User Organization Roles

    Get list of all organization roles for a user.

  • Get User Organization Role

    Get user role detail in a specific organization.

Other (19)

  • Create Device Request

    Initiate a device creation request.

  • List LLM Providers

    Retrieve available LLM providers for AI agents.

  • Get Connection Editable Schema

    Get list of connection parameters that can be updated.

  • List Devices

    Get list of devices for a team.

  • List Keys

    Get the list of keys in your custom keychain.

  • Get Organization Subscription

    Retrieve current active subscription information.

  • Get Organization Usage

    Retrieve daily usage metrics for an organization.

  • Get Team Usage

    Retrieve daily usage metrics for a team over the past 30 days.

  • Get Current User

    Retrieve data about the authenticated user.

  • List User Roles

    Retrieve list of all existing user role names and IDs.

  • List AI Agent Scenarios

    Retrieve scenarios containing AI agent modules.

  • Update Connection Data

    Update connection parameters.

  • Run AI Agent

    Run an AI agent with messages.

  • Rename Connection

    Update a connection's name.

  • Verify Connection

    Verify the connection status.

  • Verify Connection Scoped

    Verify if a connection has the required scopes.

  • Start Scenario

    Start the specified scenario.

  • Stop Scenario

    Stop the specified scenario.

  • Run Scenario

    Run the specified scenario immediately.

Set Up Your Make MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Make in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More Workflow Automation MCP Servers

Fivetran

144+ actions

Talend

60+ actions

All Workflow Automation MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

Make MCP Server FAQ

Does StackOne have a Make MCP server?
Yes. StackOne offers a hosted Make MCP server with 58 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Make MCP server vs direct API integration — what's the difference?
A Make MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Make. A Make MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Make at runtime. StackOne provides both.
How does Make authentication work for AI agents?
Make authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Make account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Make MCP tools vulnerable to prompt injection?
Yes — Make MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Make agent and how do I avoid it?
Context bloat happens when Make tool schemas and API responses eat your Make agent's memory, preventing it from reasoning effectively. A single Make query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Make agent can access?
Yes — you can limit which actions your Make agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Make MCP server?
Yes — you can create custom agent actions for your Make MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Make's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Make MCP server?
Skip a Make MCP server if your integration is purely software-to-software — direct Make API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Make actions at runtime.
What AI frameworks and AI clients does the StackOne Make MCP server support?
The StackOne Make MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo