MCP in both directions

What it is

The Model Context Protocol is the emerging standard for connecting agents to tools, and Flowable now speaks it in both directions. Flowable can reach out and call tools hosted on remote MCP servers, and Flowable can present itself as an MCP server so that external AI assistants act on the work and models inside it. These are two independent capabilities, and you can use either on its own.

Consuming external MCP tools

A remote MCP server is modeled as a service in Flowable Design, which makes its tools part of your business logic. You can call an MCP tool from a process or case as a service task, and you can give an agent the same tool to use during a run.

Discovery happens once, at design time. Flowable Design detects the server’s tools and turns them into operations in the service definition, so you do not transcribe them by hand. From that point the tool set is fixed and deterministic. Agents do not discover or gain new tools at run time, they only see the tools that were captured in the definition. Unwanted tools can be removed from the MCP service definition, and an agent then does not see them at all, so the set of tools an agent can use stays under your control.

What’s included:

• Configure a remote MCP server as a service in Flowable Design.
• Automatic tool discovery at design time, so the server’s tools are detected and turned into operations in one step.
• A fixed, deterministic tool set: agents use exactly the tools captured in the definition and never discover new ones at run time.
• Curate the surface by removing unwanted tools from the service definition, after which an agent cannot see or call them.
• Use MCP tools as part of business logic, as a service task inside a BPMN process or a CMMN case.
• Use the same MCP tools directly from an agent during its run.

Exposing Flowable Work as an MCP server

Flowable Work exposes its runtime capabilities, such as user tasks and process and case information, as MCP tools. A business user can connect their own assistant and have it act on the work running inside Flowable, without leaving the tools they prefer to work in.

What’s included:

Through the Work MCP server, a connected assistant can:

• Work on tasks: find the tasks a user can see, and complete them, including submitting form data and choosing an outcome.
• Start and follow work: start a process or a case, and read both running and completed instances.
• See what can be started: list the deployed processes and cases available to run.

Exposing Flowable Design as an MCP server

Flowable Design exposes its modeling capabilities as MCP tools. A modeler can connect their own assistant and have it help build and change models, the processes, cases, forms and other definitions, from outside the Design UI.

What’s included:

Through the Design MCP server, a connected assistant can:

• Organise the modeling space: browse and manage workspaces, and the apps and plugins inside them.
• Build and change models: create, duplicate, rename, lock and delete models, and edit the content of BPMN processes, CMMN cases, DMN decisions, forms, pages and all other model types.
• Validate before publishing: check a model for errors.
• Publish: deploy an app to a running environment.

Why it matters

Agents are only as useful as the tools they can reach. Consuming remote MCP servers means Flowable is not limited to what the platform ships, it extends into whatever an organisation already runs, with no custom integration code. Exposing Flowable as an MCP server serves two different audiences: business users can drive runtime work through Flowable Work as a set of tools, and modelers can shape business logic through Flowable Design as a set of tools. In both cases the user can only do through MCP what they are already allowed to do in the product.