Retry a failing workflow (MEDIUM RISK - may DEFER if loop threshold exceeded)
AI agents invoke retry-workflow to trigger actions in Stage0 Authorization MCP Server. 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 a workflow (an external operation whose effects depend on context and arguments), placing it in the Execute category. Severity is high because retrying workflows could consume resources, trigger downstream integrations, or repeat partially-completed operations.
From the tool's definition 'Retry a failing workflow' describes an action that triggers external operations—specifically re-executing a previously-failed workflow.
Attacks that exploit this kind of access
Retry a failing workflow (MEDIUM RISK - may DEFER if loop threshold exceeded). It is categorised as a Execute tool in the Stage0 Authorization MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Stage0 Authorization MCP Server MCP server in PolicyLayer and add a rule for retry-workflow: 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 Stage0 Authorization MCP Server. Nothing to install.
retry-workflow 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 retry-workflow 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 retry-workflow. 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.
retry-workflow is provided by the Stage0 Authorization MCP Server MCP server (starlight143/mcp-server-stage0-authorization). 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 →