retry_sites
Re-run generation for FAILED sites in a project (the MCP equivalent of the dashboard Retry button). Pass onlyFailed: true to retry every failed/cancelled site, or siteIds: [...] to retry specific ones. Only sites in a failed/cancelled state are retried; others are reported under skipped. Use list...
This record as markdown: /tools/a3plus-mcp/retry-sites.md
What retry_sites does on A3plus
AI agents invoke retry_sites to trigger actions in A3plus. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
siteIds | array | — | Specific site IDs to retry (alternative to onlyFailed). |
projectId | string | Yes | The A3Plus project ID. |
onlyFailed | boolean | — | Retry ALL failed/cancelled sites in the project. |
Parameters from the server's own tool schema.
Why retry_sites is rated High
retry_sites triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs retry_sites safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For retry_sites, this is the rule to start with:
retry_sites stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every retry_sites call is checked against it from then on.
Questions about retry_sites
Re-run generation for FAILED sites in a project (the MCP equivalent of the dashboard Retry button). Pass onlyFailed: true to retry every failed/cancelled site, or siteIds: [...] to retry specific ones. Only sites in a failed/cancelled state are retried; others are reported under skipped. Use list_sites first to see statuses. It is categorised as a Execute tool in the A3plus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
retry_sites accepts 3 parameters: siteIds, projectId, onlyFailed. Required: projectId. The full parameter table on this page comes from the server's own tool schema.
Register the A3plus MCP server in PolicyLayer and add a rule for retry_sites: 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 A3plus. Nothing to install.
retry_sites 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_sites 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_sites. 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_sites is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A3plus, and thousands of servers like it.
Across the catalogue