// MCP TOOL REFERENCE

AGENT WORKFLOW ENGINE TOOLS

5 tools from the Agent Workflow Engine MCP Server, categorised by risk level.

View the Agent Workflow Engine policy → Token cost: 582 tokens →

// ALL 5 AGENT WORKFLOW ENGINE TOOLS

READ 1 tools

Read get_workflow_status Decode a workflow_token and return full status summary.

WRITE 4 tools

Write auto_route_next_step Advance to the next workflow step, evaluating conditional branches. Returns next_agent and updated workflow... Write create_workflow Create a new multi-agent workflow. Returns a workflow_token encoding the full state — pass it to all subseq... Write set_conditional_branch Attach a conditional branch to a step. Operator is evaluated against agent output when routing. Returns upd... Write track_agent_state Update agent execution state. Returns updated workflow_token.

// FAQ

How many tools does the Agent Workflow Engine MCP server have? +

The Agent Workflow Engine MCP server exposes 5 tools across 2 categories: Read, Write.

How do I enforce policies on Agent Workflow Engine tools? +

Route the Agent Workflow Engine server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Agent Workflow Engine tools fall into? +

Agent Workflow Engine tools are categorised as Read (1), Write (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.