What AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

How do I trigger a flow?

You can use the execute_flow capability by providing the required JSON payload that matches your flow's Request Schema.

Can I debug failed workflows?

Yes, you can use the get_execution capability to retrieve a full, step-by-step trace of any execution.

How do I manage my API credentials?

The MCP includes capabilities to store, retrieve, and rotate credentials for your various connectors.

Can I see how much of my quota I have left?

Yes, you can check your current usage, daily breakdown, or a full summary using the quota capabilities.

Can I trigger a flow and get the result immediately?

Yes. Use the execute_flow capability with the flow name and input data. It performs a real-time sync execution and returns the response directly to the agent.

How can I debug a failed flow execution?

You can use list_executions to find the ID of the failed run, then use get_execution to retrieve a full step-by-step trace of what happened during that specific execution.

Is it possible to update an existing workflow definition?

Absolutely. The update_workflow capability allows you to modify the JSON definition of any flow. Remember to use publish_workflow afterwards to deploy your changes to the live environment.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Fastn to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your low-code workflows using natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 16 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 16 available through Fastn.

01
Get credentials
Retrieves your stored connector credentials.
02
Get execution
Fetches a complete, step-by-step trace for a specific execution.
03
Get quota usage
Checks your current usage against your plan limits.
04
Get workflow
Returns the full specification for a specific flow.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 16 available through Fastn.

05
Publish workflow
Deploys or publishes a defined flow.
06
Store credentials
Saves new credentials for your connectors.
07
Update workflow
Modifies an existing flow definition.
08
Archive workflow
Deactivates or archives a flow.

Capability set03 / 04

09-12

4 capabilities in this set.

Part of 16 available through Fastn.

09
Cancel execution
Stops a currently running execution.
10
Create workflow
Generates a new flow definition.
11
Execute flow
Triggers a Fastn flow immediately using a JSON payload.
12
Get quota daily
Provides a breakdown of your daily usage.

Capability set04 / 04

13-16

4 capabilities in this set.

Part of 16 available through Fastn.

13
Get quota summary
Returns a summary of your total usage.
14
List executions
Lists the execution history for a specific tenant.
15
List workflows
Shows all flow definitions within a tenant.
16
Rotate credentials
Rotates existing credentials for your integrations.

Real work

What teams actually run

Rapid Flow Testing

Send custom JSON payloads to a flow to verify logic immediately.

Automated Debugging

Ask your agent to find why a specific execution failed by pulling its trace.

Environment Maintenance

Update or archive workflows as your business logic evolves.

Security Operations

Rotate connector credentials through the agent to maintain security.

Automate a task

Put Fastn to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Fastn works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Fastn to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1017ms average. Fast in production.

Fastn is checked daily against the live service.

Daily averagePeak 1121ms

Oct 3Today

Fastest day: 773ms
Slowest day: 1121ms
14-day trend: Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 16 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Fastn, so you can see the experience inside your AI.

It does not authenticate your account with Fastn. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Fastn Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_wa4bKnlUgLKkNcgy1RPaz1zwlTmtw2evOT0C54sb/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Fastn capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "fastn-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_wa4bKnlUgLKkNcgy1RPaz1zwlTmtw2evOT0C54sb/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Fastn in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Fastn owners hand off.

This MCP is built for technical teams managing low-code backend logic through Fastn.

01
Developers
Trigger and test flows without leaving the code editor.
02
DevOps Engineers
Monitor execution traces and manage environment credentials.
03
Product Teams
Check automation statuses and trigger business logic via conversation.

FAQ

Questions Fastn owners ask.

01
What AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
02
How do I trigger a flow?
You can use the execute_flow capability by providing the required JSON payload that matches your flow's Request Schema.
03
Can I debug failed workflows?
Yes, you can use the get_execution capability to retrieve a full, step-by-step trace of any execution.
04
How do I manage my API credentials?
The MCP includes capabilities to store, retrieve, and rotate credentials for your various connectors.
05
Can I see how much of my quota I have left?
Yes, you can check your current usage, daily breakdown, or a full summary using the quota capabilities.
06
Can I trigger a flow and get the result immediately?
Yes. Use the execute_flow capability with the flow name and input data. It performs a real-time sync execution and returns the response directly to the agent.
07
How can I debug a failed flow execution?
You can use list_executions to find the ID of the failed run, then use get_execution to retrieve a full step-by-step trace of what happened during that specific execution.
08
Is it possible to update an existing workflow definition?
Absolutely. The update_workflow capability allows you to modify the JSON definition of any flow. Remember to use publish_workflow afterwards to deploy your changes to the live environment.

Explore

More in Developer Tools

Connect Fastn to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get credentials

Get execution

Get quota usage

Get workflow

05-08

Publish workflow

Store credentials

Update workflow

Archive workflow

09-12

Cancel execution

Create workflow

Execute flow

Get quota daily

13-16

Get quota summary

List executions

List workflows

Rotate credentials

What teams actually run

Rapid Flow Testing

Automated Debugging

Environment Maintenance

Security Operations

Building your own app? The connector is yours to use.

Fastn Connector

Claude Desktop

Developers

DevOps Engineers

Product Teams

What AI clients can I use with this MCP?

How do I trigger a flow?

Can I debug failed workflows?

How do I manage my API credentials?

Can I see how much of my quota I have left?

Can I trigger a flow and get the result immediately?

How can I debug a failed flow execution?

Is it possible to update an existing workflow definition?

n8n (AI Workflow Automation) AI Connector

Flowise AI Connector

Make (Workflow Automation) AI Connector

Relay Workflow Automation AI Connector

Suggestions

ServiceNow AI Connector

Kissflow AI Connector

Nutrient Workflow AI Connector

Tray.io AI Connector