workflow_retry_policy
Configure a global retry policy with exponential backoff for workflow steps. The stored policy is applied by run_extension_workflow / run_macro when individual nodes lack an explicit retry config. Returns the normalised policy.
This record as markdown: /tools/io-github-vmoranv-jshookmcp/workflow-retry-policy.md
What workflow_retry_policy does on Jshookmcp
AI agents use workflow_retry_policy to create or update resources in Jshookmcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jshookmcp environment.
Why workflow_retry_policy is rated Medium
Modifies stored retry policy configuration applied globally, affecting workflow behavior reversibly.
From the tool's definition Configure global retry policy applied to workflow steps, stored state modification
Attacks that exploit this kind of access
The rule that runs workflow_retry_policy safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Jshookmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For workflow_retry_policy, this is the rule to start with:
workflow_retry_policy stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Jshookmcp, apply this rule, and every workflow_retry_policy call is checked against it from then on.
Questions about workflow_retry_policy
Configure a global retry policy with exponential backoff for workflow steps. The stored policy is applied by run_extension_workflow / run_macro when individual nodes lack an explicit retry config. Returns the normalised policy. It is categorised as a Write tool in the Jshookmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jshook MCP server in PolicyLayer and add a rule for workflow_retry_policy: 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 Jshookmcp. Nothing to install.
workflow_retry_policy is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the workflow_retry_policy 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 workflow_retry_policy. 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.
workflow_retry_policy is provided by the Jshook MCP server (@jshookmcp/jshook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Jshook, and thousands of servers like it.
This server
Across the catalogue