Connect your AI Agents to Make in minutes
Available tools
list_connections
List connections for a team. Requires teamId - use list_teams first to get valid team IDs.
get_connection
Get connection details by ID including account info and scopes. Use list_connections first to find valid IDs.
delete_connection
Delete a connection. Set confirmed=true if the connection is used in scenarios to force deletion.
verify_connection
Verify a connection is working by testing it against the external service. Returns verified=true if successful.
list_hooks
List webhooks for a team. Requires teamId - use list_teams first. Filter by assigned status or hook type.
get_hook
Get webhook details by ID including URL, status, and queue info. Use list_hooks first to find valid IDs.
create_hook
Create a new webhook to receive external data. Set method, headers, and stringify options for request handling.
update_hook
Update webhook name or enabled status. Use get_hook first to see current values.
delete_hook
Delete a webhook. Set confirmed=true if the hook is used in scenarios to force deletion.
enable_hook
Enable a webhook to start receiving data. The hook URL will accept incoming requests.
disable_hook
Disable a webhook to stop receiving data. Incoming requests will be rejected until re-enabled.
list_organizations
List organizations the authenticated user has access to. Use this to get organization IDs for other operations.
get_organization
Get organization details by ID including license info and datacenter zone. Use list_organizations first.
list_apps
List installed apps for an organization. Use appName values as accountType when creating connections with create_connection.
list_scenarios
List scenarios in a team with optional filtering by folder, active status, or type. Use list_organizations and list_teams first to get valid IDs.
get_scenario
Get scenario details by ID including blueprint, scheduling, and status. Use list_scenarios first to find valid scenario IDs.
create_scenario
Create a new scenario. Blueprint needs 'name', 'flow', 'metadata.version'. Use scheduling type 'on-demand' for manual trigger or 'indefinitely' with interval for recurring.
update_scenario
Update scenario name, blueprint, scheduling, or folder. Use get_scenario first to see current values.
delete_scenario
Permanently delete a scenario. This action cannot be undone. Use get_scenario to verify before deletion.
run_scenario
Execute a scenario immediately with optional input data. Set responsive=true to wait for results.
start_scenario
Activate a scenario to enable scheduled execution. The scenario will run according to its scheduling configuration.
stop_scenario
Deactivate a scenario to stop scheduled execution. The scenario can be reactivated later with start_scenario.
clone_scenario
Clone a scenario to a new team. Use list_organizations and list_teams to get valid target IDs.
list_teams
List teams in an organization. Requires organizationId - use list_organizations first to get valid IDs.
get_team
Get team details by ID. Use list_teams first to find valid team IDs.
create_team
Create a new team. May require license upgrade if team limit reached. Requires organizationId from list_organizations.
delete_team
Delete a team. This will delete all scenarios, connections, and hooks in the team. Cannot be undone.
validate_credential
Validate Make credentials. Verifies credentials during setup.
How to set up Merge Agent Handler
In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}FAQs on using Merge's Make MCP server
FAQs on using Merge's Make MCP server
What is a Make MCP?
It's an MCP server that connects your agents to Make's automation platform via tools. Your agents can invoke these tools to trigger scenario runs, create and update webhook endpoints, manage app connections, inspect scenario configuration, and more.
Make offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.
How can I use the Make MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- On-demand scenario execution: When a specific event occurs in a product (like a new enterprise sign-up), an agent triggers the corresponding onboarding scenario in Make without requiring any manual intervention or scheduled run
- Webhook lifecycle management: An agent creates or updates a Make webhook endpoint in response to a configuration change in another service, keeping automation pipelines in sync without manual re-setup in the Make UI
- Scenario health monitoring: On a scheduled basis, an agent queries Make for scenarios that have errored or stopped, then posts a failure summary to an ops Slack channel so engineers can investigate
- Cross-platform orchestration: An agent receives a stage change signal from a CRM like HubSpot, then triggers the relevant Make scenario to kick off a downstream workflow across multiple connected tools
What are popular tools for Make's MCP server?
Here are some of the most commonly used tools:
run_scenario: executes a Make scenario on demand, bypassing Make's own trigger schedule. Call this when an agent needs to kick off an automation pipeline in response to an external event
list_scenarios: retrieves all scenarios in an organization along with their current status. Useful for agents that need to audit active automations or identify which scenario handles a given workflow
get_scenario: fetches configuration and execution details for a single scenario. Use this when an agent needs to verify a scenario's settings before running or modifying it
create_hook: registers a new webhook endpoint in Make tied to a scenario. Call this when an agent needs to wire up an inbound trigger from another system to an existing Make scenario
list_connections: retrieves all authenticated app connections in a Make organization. Good for agents that need to confirm required third-party credentials are in place before executing a scenario
create_scenario: creates a new automation scenario in Make. Helpful when an agent is provisioning automation infrastructure as part of a broader onboarding or configuration workflow
What makes Merge Agent Handler's Make MCP server better than alternative Make MCP servers?
A few things differentiate Merge Agent Handler's Make MCP server from building your own or using a community alternative:
- Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Make, this means you can prevent scenario configuration details, connection credentials, and webhook payloads from being exposed even when the agent has broad read access
- Managed authentication and credentials: Merge stores and refreshes Make credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually
- Real-time observability and audit trail: Every tool call made against Make is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly which scenarios an agent triggered or modified without instrumenting anything yourself
- Tool Packs and controlled access: Tool Packs let you bundle specific Make tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more
How can I start using Merge Agent Handler's Make MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account.
2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.
3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.
4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Make and complete the auth flow. Merge stores and manages the credentials going forward.
5. Open a Claude Code session and start querying Make data directly. The first time you use a Make tool, a Magic Link may appear to complete connector authentication.
If you want to connect Merge Agent Handler's Make MCP with internal or customer-facing agentic products, you can follow the steps in our docs.
Ready to try it out?
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now
