Activepieces MCP. Manage your entire automation engine via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Activepieces MCP gives your AI agent control over entire automation workflows. Manage complex flows, monitor execution logs, and handle app credentials—all through natural language prompts.
You can list projects, create new automations, and update connections for services like Slack or Google Sheets without touching a dashboard.
What your AI agents can do
Add piece
Adds a custom component or piece of logic to an automation flow.
Apply flow operation
Applies structural changes, like moving actions or changing the status of an entire workflow.
Configure git repo
Sets up Git synchronization for a project to manage code versioning.
Create, read, update, or delete entire automated workflows within specific projects.
Check the status and inspect detailed results of any completed or failing workflow run.
List, create, or delete credentials for external services like Slack or Google Sheets used by your flows.
Create and manage folders and projects to keep all automation logic tidy.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Activepieces: 32 Tools for Workflow Control
These tools let you manage every component of your activepieces workspace, from creating new projects and managing connections to controlling individual automation flows.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Activepieces on Vinkius019e3860add piece
Adds a custom component or piece of logic to an automation flow.
019e3860apply flow operation
Applies structural changes, like moving actions or changing the status of an entire workflow.
019e3860configure git repo
Sets up Git synchronization for a project to manage code versioning.
019e3860create flow
Builds and registers an entirely new automation workflow in your account.
019e3860create folder
Creates a dedicated container to help organize multiple related projects or flows.
019e3860create project
Initializes and registers an entirely new workspace for automation development.
019e3860create project release
Creates a specific, versioned snapshot of your project settings or code.
019e3860delete app connection
Removes the credentials for one external service used by your automation flows.
019e3860delete flow
Permanently removes an existing workflow from your system using its ID.
019e3860delete folder
Removes a folder, taking all contained projects and flows with it.
019e3860delete global connection
Clears out a connection that is shared across multiple different projects in the account.
019e3860delete project member
Revokes access by removing another user from an existing project workspace.
019e3860get flow
Retrieves all the configuration details for a specific automation flow ID.
019e3860get flow run
Pulls detailed execution data, showing every step and result of a single workflow run.
019e3860get mcp server
Retrieves the configuration details for the MCP connection itself for your AI client.
019e3860invite user
Sends an invitation to a user account so they can access specific projects or the entire platform.
019e3860list app connections
Lists every external service connection (like Slack) that your automation platform uses.
019e3860list flow runs
Generates a list of all recent workflow executions, showing success or failure status.
019e3860list flows
Lists every current automation flow that is active within the project workspace.
019e3860list folders
Retrieves a list of all organizational folders you have created in your account.
019e3860list global connections
Shows all global credentials available across the entire Activepieces platform.
019e3860list project members
Lists every user who currently has access permissions within a specific project.
019e3860list projects
Retrieves a list of all the separate project workspaces you have set up.
019e3860list records
Queries and displays content from an internal data table within your activepieces workspace.
019e3860list tables
Displays a list of all the underlying, structured data tables available in the platform.
019e3860list users
Retrieves a directory listing of user accounts across the Activepieces platform.
019e3860rotate mcp token
Generates and updates an access token for the MCP connection to maintain security.
019e3860update folder
Changes the name or metadata of an existing organizational folder.
019e3860update project
Modifies general settings for a project, such as its name or description.
019e3860update record
Changes the content of specific data records within an internal table.
019e3860upsert app connection
Creates a new external service connection or updates an existing one using credentials like OAuth2.
019e3860upsert global connection
Creates or replaces a global credential set used across multiple projects for platform services.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Activepieces, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Activepieces. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 32 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Tracking down why an automated process broke is tedious.
Right now, if a key workflow stops working, you're stuck in a loop of tabs: checking the project overview, digging into execution logs, and then manually trying to figure out which step failed. You copy data from one screen, open another tab to check credentials, and paste it back—a process that takes minutes just to diagnose.
With this MCP, you tell your agent what's wrong. It finds the flow ID using `list_flows`, pulls the error details with `get_flow_run`, and tells you exactly which credential needs updating via `list_app_connections`. The diagnosis happens in one conversation.
Get full control over your automation resources using Activepieces MCP.
You no longer need to manually navigate the UI just to structure your workspace. You can ask the agent to list all current projects, create a new project for Q3 initiatives, and then run `create_folder` inside it. It's instant setup.
This gives you full programmatic control over your automation lifecycle. Your AI client treats your entire workflow system—the folders, the flows, the connections—as just another API resource to manage.
What you can do with this MCP connector
Need to manage business logic that runs across multiple apps? This MCP connects your AI client directly to the Activepieces platform, turning your automation back-office into an accessible tool. Instead of logging into the web UI just to check if a lead flow broke or update a credential, you tell your agent to do it.
It can list all active flows and even apply structural changes programmatically, like pausing a whole sequence or adding a new step. If you're building complex automations that need to talk to a CRM, then send data to a messaging service, this MCP is key because Vinkius allows you to chain together multiple MCPs; your AI agent can manage the entire pipeline from one connection point.
You use it to check which flows are running and retrieve detailed logs for debugging, making your automation platform just as responsive as any other tool in your stack.
019e3860-7a7d-71ef-b884-e518f1a812d3 
How Activepieces MCP Works
- 1 Subscribe to the Activepieces MCP and enter your API key.
- 2 Connect that single connection from Claude, Cursor, or any other AI client.
- 3 Use natural language prompts telling your agent exactly which flow needs checking or what new folder you need created.
The bottom line is, your AI acts as a dedicated automation engineer who lives inside the platform, managing resources and code paths for you.
Who Is Activepieces MCP For?
This MCP is built for the Ops Engineer who spends too much time manually checking execution logs or Product Managers who need to verify data consistency across several automated systems. It’s for anyone whose job involves managing workflows, not just running them.
Monitoring flow health and triggering updates directly through chat or terminal commands.
Verifying data consistency across automated workflows and managing app connections for business tools.
What Changes When You Connect
- You can track failures and diagnose issues instantly. Instead of clicking through logs, ask the agent to list flow runs or get detailed execution data using
list_flow_runsorget_flow_run. The results show exactly where a step failed. - Manage your core infrastructure without touching a dashboard. Need to pause an automation? Use
apply_flow_operationto change its status, or usedelete_flowif the entire workflow is deprecated. - Keep your credentials safe and up-to-date. You can list all app connections with
list_app_connectionsand then securely update them usingupsert_app_connection, knowing that Vinkius handles credential passing through a zero-trust proxy, so your keys never sit on disk. - Build out complex systems by chaining services. If you need to build an automation that talks to Slack and updates Google Sheets, your agent can manage the flows and connections for both platforms in one session.
- Keep data clean and organized at scale. Use
list_projectsorcreate_folderto scope your work, ensuring every new flow gets put into the right container from day one.
Real-World Use Cases
Debugging a Failed Lead Flow
A Product Manager noticed a critical lead-gen workflow stopped sending notifications. They ask their agent to list all active automation flows and then pull the detailed run data using get_flow_run for yesterday's date, quickly identifying that an app connection needed updating.
Onboarding a New Service
An Ops Engineer needs to integrate Stripe into the platform. They use the agent to list existing global connections, and then run upsert_app_connection using OAuth2 credentials, making sure the new service is ready for flows.
Archiving a Deprecated Feature
The team scrapped an old reporting system. Instead of manually deleting it across three different tabs, they ask the agent to get all details about that flow using get_flow and then execute delete_flow, confirming its removal.
Scaling Project Structure
A growing business needs separation between sales automations and marketing funnels. The agent helps them list current projects, create a new project workspace for Marketing, and guide them through creating the initial folder structure using create_folder.
The Tradeoffs
Trying to delete everything at once
Asking the agent to 'delete all old stuff.' This vague command could lead it to accidentally remove critical global connections or active projects.
→
Be specific. First, use list_projects to confirm which project you're working in. Then, target the resource: run delete_flow on the exact ID of the flow you want gone.
Manually updating credentials
A user needs to change a Slack API key and has to navigate to settings, find the app connection, and paste the new secret manually.
→
Use upsert_app_connection with your agent. Specify 'Slack' as the service and provide the updated credentials in one prompt. It handles the whole process.
Changing a flow without testing
The team runs apply_flow_operation to change how data moves, but forgets to test it with a real run, leading to silent failures downstream.
→
Always check the impact first. Run list_flow_runs for recent history, then ask the agent to apply the operation and immediately follow up by getting the flow details using get_flow.
When It Fits, When It Doesn't
Use this MCP if your primary need is managing the infrastructure of your automations. If you need to create a new project, list existing flows, or change credentials for an external service, this is your tool. Don't use it if you simply need to read raw data; for that, check list_records and list_tables. Avoid using the flow management tools (like create_flow or delete_flow) when you just want a simple list of users; instead, run list_users. This MCP is about controlling the automation layer itself, not just querying data from it.
Common Questions About Activepieces MCP
How do I check if a flow failed using list_flow_runs? +
You ask the agent to run list_flow_runs. The output will show a status column. If it shows 'Failed,' you can then use get_flow_run with the specific run ID to see the exact step that tripped up.
What is the difference between list_flows and get_flow? +
list_flows gives you a directory listing of all active flows in your project. get_flow, however, retrieves every single piece of configuration data for one specific flow ID.
Can I update credentials using upsert_app_connection? +
Yes. You use the agent to call upsert_app_connection. This tool lets you either create a brand new connection or overwrite an existing one, so you don't have to delete and re-add it manually.
If I want to remove a whole project workspace, what tool should I use? +
There isn't one single 'delete project' function. You first need to manage the resources inside: list all flows using list_flows, and then run delete_flow on each component individually.
How do I fetch a list of specific records from an internal table using `list_records`? +
You pass the desired table name and criteria to the tool. This function reads structured data directly, letting your agent pull details like user IDs or product codes without manual database queries.
What information does `list_global_connections` provide regarding my workspace integrations? +
It shows all high-level connections that apply across the entire platform. This helps you audit and manage credentials like API keys or OAuth tokens before they're used in a specific project.
What types of structural changes can I make to an existing flow using `apply_flow_operation`? +
You can apply specific operations, such as moving the entire flow or changing its status (e.g., turning it off). This lets your agent manage workflow structure without needing manual UI clicks.
How do I check all registered accounts on the system using `list_users`? +
This tool lists every user account associated with the platform. It’s useful for giving an overview of who has access or checking if a specific team member needs to be invited.
Can I check why a specific flow execution failed? +
Yes. Use the get_flow_run tool with the Run ID to retrieve detailed execution data, including step results and error messages.
How do I update the status of an existing flow? +
You can use the apply_flow_operation tool. It allows you to send an operation payload to change the flow's status or modify its structure.
Can I see which external apps are connected to my project? +
Yes, the list_app_connections tool retrieves all credentials and connections configured for a specific Project ID.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.