Connect your own AI agent to FlowFuse

You can now connect your own AI agent to FlowFuse. Your company-approved AI can manage your platform and build Node-RED applications for you.

Add the FlowFuse address to connect, then decide which teams the agent reaches and whether it can make changes.

Pick your agent, and follow the three steps:

Copy the FlowFuse connector URL

You will paste this into your agent in the next step.

https://app.flowfuse.com/mcp

Copilot Studio, Tools, Add a tool

Choose Model Context Protocol and paste the URL. Describe what it is for: the orchestrator reads that to decide when to call it.

Open Copilot Studio

Which teams the agent may act on, and whether it has editing rights or read access only.

Try it out

Copy the FlowFuse connector URL

You will paste this into your agent in the next step.

https://app.flowfuse.com/mcp

Settings, Apps & Connectors, Advanced settings

Turn on developer mode there, then add FlowFuse by URL. Developer mode needs a paid plan, so it is not on the free tier.

Open ChatGPT

Which teams the agent may act on, and whether it has editing rights or read access only.

Try it out

Copy the FlowFuse connector URL

You will paste this into your agent in the next step.

https://app.flowfuse.com/mcp

Add a custom connector

Where custom connectors are available on your plan, add one and paste the URL. On Team and Enterprise an owner adds it once for everyone.

Open Claude

Which teams the agent may act on, and whether it has editing rights or read access only.

Try it out

Copy the FlowFuse connector URL

You will paste this into your agent in the next step.

https://app.flowfuse.com/mcp

Your MCP client's config

Any MCP-capable client works, pointed at your own model, so nothing has to leave your network.

See the documentation

Which teams the agent may act on, and whether it has editing rights or read access only.

Try it out

Any MCP client that supports the HTTP transport works, including command-line and editor agents and local models. Sign-in uses OAuth where the client supports it, with a token fallback where it does not.

Your own agent gets the full, growing set of FlowFuse platform automation and flow-building tools to run. That matters most where company policy only permits an approved AI agent, so FlowFuse Expert wasn't an option.

Your grant is enforced on every call: a read-only agent stays read-only, and no agent can delete an instance, application, snapshot or team. Every action is recorded in the audit log, marked via MCP.

When the agent builds a flow, you watch it happen on the canvas: open the instance and turn on the MCP toggle in the page header. Nothing goes live until you deploy.

This is available to all FlowFuse Cloud users and to Enterprise self-hosted installations from v3.0, across FlowFuse Hub, Edge and Fleet. See connecting your own agent for setup, including what to check on an instance before asking for a flow.

Written By:

Related GitHub Issues

Recent Updates:

Sign up for updates