Retry a failed run, resuming from the step that failed. Completed steps are memoized and NOT re-executed — the run picks up where it left off. Use this after a transient failure (network blip, rate limit) where you want to preserve prior progress. For a clean re-execution that runs every step fro...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Flowforge server.
Free to start. No card required.
AI agents invoke flowforge_retry_run to trigger processes or run actions in Flowforge. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
flowforge_retry_run can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"flowforge_retry_run": {
"limits": [
{
"counter": "flowforge_retry_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Flowforge policy for all 49 tools.
These attack patterns abuse exactly the kind of access flowforge_retry_run gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Retry a failed run, resuming from the step that failed. Completed steps are memoized and NOT re-executed — the run picks up where it left off. Use this after a transient failure (network blip, rate limit) where you want to preserve prior progress. For a clean re-execution that runs every step from scratch (e.g. after fixing the function's code), use flowforge_replay_run instead.. It is categorised as a Execute tool in the Flowforge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Flowforge MCP server in PolicyLayer and add a rule for flowforge_retry_run: 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 Flowforge. Nothing to install.
flowforge_retry_run 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 flowforge_retry_run 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 flowforge_retry_run. 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.
flowforge_retry_run is provided by the Flowforge MCP server (flowforge-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 49 Flowforge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.