Check the health of a connected social account on PostEverywhere. Returns status (healthy|warning|broken), can_post boolean, token expiry, needs_reconnection flag, recent failure count, last successful publish. Use this before publishing to detect a dead token BEFORE it causes a failed post.
AI agents call get_account_health to retrieve information from Posteverywhere without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_account_health is a diagnostic read operation that queries account state without modifying, executing, or deleting anything. It retrieves status information to inform decision-making before publishing. The severity is low because even if misused, it only exposes account health metadata without enabling harmful actions directly.
From the tool's definition Tool returns status information: 'Returns status (healthy|warning|broken), can_post boolean, token expiry, needs_reconnection flag, recent failure count, last successful publish.' These are all read operations retrieving account health metadata with no side…
Attacks that exploit this kind of access
Check the health of a connected social account on PostEverywhere. Returns status (healthy|warning|broken), can_post boolean, token expiry, needs_reconnection flag, recent failure count, last successful publish. Use this before publishing to detect a dead token BEFORE it causes a failed post. It is categorised as a Read tool in the Posteverywhere MCP Server, which means it retrieves data without modifying state.
Register the Posteverywhere MCP server in PolicyLayer and add a rule for get_account_health: 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.
get_account_health is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_account_health 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 get_account_health. 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.
get_account_health 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.
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 →