FlowFuse MCP Server

FlowFuse exposes an MCP server. An AI agent connects as a client to operate the platform and build flows.

Two clients use it:

  • FlowFuse Expert, the AI built into the platform and the Node-RED editor.
  • Your own agent, such as Microsoft Copilot, ChatGPT or Claude, connected over the MCP endpoint.

Both use the same capabilities. What an agent can do depends only on the access you grant.

Note: This is not the same as MCP server nodes, which build MCP servers inside your flows. This page is about operating FlowFuse itself, where FlowFuse is the server and your agent is the client.

Platform Automations

Actions an agent can take on the platform, by resource and access level.

ResourceRead-onlyFull access
TeamsMembers and roles, invitations, audit log, resource counts, bill of materialsCreate a team, update settings, change member roles, invite and re-invite members
ApplicationsApplications, audit log, device groups, bill of materialsCreate and update applications
Hosted instancesLive status, resources, configuration, logs, files, history, HTTP tokensCreate, start, stop, restart, suspend; update settings, environment and config surfaces; import flows; edit files; manage HTTP tokens
Remote instancesRemote instances and live statusRegister and assign to an application, restart, update settings and operating mode
SnapshotsSnapshots, including full flowsCreate, export, import, update; set an instance's device target
PipelinesPipelines and stagesCreate and update pipelines; add, update and deploy stages
Device groupsTeam and application device groupsCreate and update groups, change membership and settings
FlowFuse TablesDatabases, tables, schemas, row dataTable data is changed through flows, see Flow Building
Team brokerBrokers, clients, topics, schemaStart, stop, suspend the broker agent; create and update topics
Your accountProfile, notifications, invitationsUpdate profile, mark notifications read, respond to invitations
Blueprints and templatesBlueprints, templates, instance and team typesStarting points for creating instances and teams

Ask the agent what it can do in a given team or instance. Its tools reflect the access granted and the instance it is connected to.

Flow Building

An agent builds and edits flows inside a running Node-RED instance.

Flow work runs in a live editor session, not as a file to import. Point the agent at an open editor session and it builds on the canvas. Node-RED validates as it goes, so the agent catches its own mistakes.

AreaRead-onlyFull access
NodesRead nodes with validation stateAdd, update and remove nodes
WiringWire nodes on a tab, link nodes across tabs
TabsList tabsAdd, rename, enable, disable and remove tabs
Subflows and subroutinesList subflowsCreate and remove subflows, create subroutines
GroupsCreate, update, move and delete groups, change their members
PaletteRead the installed palette, describe node type propertiesOpen the palette manager to install packages
CanvasRead the full flow, list config nodes, read debug output, search and select nodesNavigate to a tab or subflow, align and distribute nodes
FlowFuse TablesQuery table dataBuild a Query Node flow that reads and writes tables

Nothing goes live until you deploy from Node-RED.

Access and permissions

Access comes at one of two levels:

  • Read-only sees everything and changes nothing.
  • Full access adds every action in the full-access columns above.

With FlowFuse Expert, an agent acts with the same access you have on the team you are working in.

With your own agent, you choose the access when you connect. Signing in over OAuth takes you to a FlowFuse page where you pick read-only or full access, scope it to all your teams or specific teams, and set an expiration date. A personal access token, for clients without a sign-in flow, carries the same read-only or full-access choice.