Execute a prompt using a pre-configured policy. Policies provide standardized execution patterns with model selection, automatic fallbacks, and cost controls. Use relay_policies_list to see available policies.
AI agents invoke relay_policy_execute to trigger actions in RelayPlane. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes prompts via pre-configured policies that select models and trigger fallbacks. While nominally a prompt execution interface, the ability to trigger automatic fallbacks and route execution across multiple AI providers creates a vector for unintended side effects or excessive API calls.
From the tool's definition Tool name contains 'execute' and description states 'Execute a prompt using a pre-configured policy' with references to 'model selection' and 'automatic fallbacks', indicating execution of LLM operations with external dependencies.
Attacks that exploit this kind of access
Execute a prompt using a pre-configured policy. Policies provide standardized execution patterns with model selection, automatic fallbacks, and cost controls. Use relay_policies_list to see available policies. It is categorised as a Execute tool in the RelayPlane MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RelayPlane MCP server in PolicyLayer and add a rule for relay_policy_execute: 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_policy_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the relay_policy_execute 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_policy_execute. 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_policy_execute 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 →