Connect AI agents to UAPF packages via the Model Context Protocol — structured, authenticated access to processes, decisions and runtime execution.
UAPF_MCP_WS_URL env varUAPF_ENGINE_URL env var · or uapf/config/uapf.ini
The UAPF Engine exposes these tools over MCP. AI agents can discover them via the describe tool or by reading the manifest.
Returns the capabilities of the connected UAPF Engine — version, supported standards, available packages.
Lists all packages available in the registry, with ID, name, version and level metadata.
Initiates a BPMN process instance with the provided variables. Returns instance ID and initial state.
Evaluates a DMN decision or decision table against the supplied input context. Returns the output values.
Resolves resource bindings for a process or task — role assignments, system integrations, service endpoints.
Returns the raw BPMN, DMN or CMMN model XML, or the manifest JSON, for a given package and artifact identifier.
Runs deep validation against JSON Schema and structural rules for a package or uploaded manifest. Returns issues list.
POST to the UAPF Engine agent registry with the agent's DID and name. Receive a one-time session key.
Connect to the MCP WebSocket endpoint. Present the session key in the handshake headers.
Call describe to get the engine manifest, then list to enumerate packages.
Use run_process and evaluate_decision to execute governed logic inside the agent's reasoning loop.
The UAPF Engine MCP server can be registered in Claude Desktop or any MCP-compatible host. Once connected, Claude can discover available packages, reason about process logic and invoke governed decisions — replacing ad-hoc instructions with structured, auditable process execution.
Engine reference implementation ↗