Validate workflow structure without making any LLM calls (free). Checks DAG structure (no cycles), dependency references, and model ID format. Does NOT validate schema compatibility between steps or prompt effectiveness - use relay_workflow_run for full validation.
AI agents call relay_workflow_validate to retrieve information from RelayPlane without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
relay_workflow_validate is a pure validation/inspection tool that performs static structural checks on workflow definitions without side effects or execution. It retrieves and analyzes workflow metadata (DAG structure, references, formats) but does not execute code, modify state, or trigger operations. This is characteristic of a Read operation—data retrieval and analysis with no side effects.
From the tool's definition Tool description states it 'Validate[s] workflow structure without making any LLM calls' and 'Checks DAG structure, dependency references, and model ID format.' The explicit statement 'Does NOT validate schema compatibility between steps or prompt…
Attacks that exploit this kind of access
Validate workflow structure without making any LLM calls (free). Checks DAG structure (no cycles), dependency references, and model ID format. Does NOT validate schema compatibility between steps or prompt effectiveness - use relay_workflow_run for full validation. It is categorised as a Read tool in the RelayPlane MCP Server, which means it retrieves data without modifying state.
Register the RelayPlane MCP server in PolicyLayer and add a rule for relay_workflow_validate: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches RelayPlane. Nothing to install.
relay_workflow_validate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the relay_workflow_validate rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for relay_workflow_validate. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
relay_workflow_validate is provided by the RelayPlane MCP server (relayplane/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →