retry_failed_posts · Posteverywhere MCP: Risk & Policy

WHAT IT DOES

What retry_failed_posts does on Posteverywhere

AI agents invoke retry_failed_posts to trigger actions in Posteverywhere. 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.

WHY IT NEEDS A POLICY

Why retry_failed_posts needs a policy

Retrying failed posts re-triggers external publish operations on platforms like Instagram, TikTok, YouTube, etc. This is an Execute action because it initiates external operations whose effects depend on arguments. The blast radius is high because a broad filter could cause mass unintended publishing across multiple platforms and accounts simultaneously.

From the tool's definition 'Retry all failed destinations on PostEverywhere that match a filter' — triggers external publishing operations across multiple social media platforms in bulk

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_failed_posts Rate-limited

retry_failed_posts 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "retry_failed_posts": {
      "limits": [
        {
          "counter": "retry_failed_posts_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Posteverywhere, so you can run agents against it safely.

FAQ

Questions about retry_failed_posts

What does the retry_failed_posts tool do? +

Retry all failed destinations on PostEverywhere that match a filter (account_id, platform, date range, or explicit post_ids). Saves you from making one retry call per failed post. Requires at least one filter — refuses to retry the entire failure history. It is categorised as a Execute tool in the Posteverywhere MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retry_failed_posts? +

Register the Posteverywhere MCP server in PolicyLayer and add a rule for retry_failed_posts: 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 Posteverywhere. Nothing to install.

What risk level is retry_failed_posts? +

retry_failed_posts is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit retry_failed_posts? +

Yes. Add a rate_limit block to the retry_failed_posts 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.

How do I block retry_failed_posts completely? +

Set action: deny in the PolicyLayer policy for retry_failed_posts. 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.

What MCP server provides retry_failed_posts? +

retry_failed_posts is provided by the Posteverywhere MCP server (posteverywhere/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.