AI agents call get_learned_voice to retrieve information from Posterly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously learned voice/caption style data from a user's account. It is a query operation that reads stored information about learned patterns without creating, modifying, deleting, or executing any external operations. The 'Get' verb and read-only nature classify it as Read category with low severity, as misuse would only expose stylistic data.
From the tool's definition Tool name 'get_learned_voice' and description 'Get the voice posterly has learned from a connected account's real published captions' indicates retrieval of already-learned data without modification or side effects.
Attacks that exploit this kind of access
Get the voice posterly has learned from a connected account’s real published captions (the. It is categorised as a Read tool in the Posterly MCP Server, which means it retrieves data without modifying state.
Register the Posterly MCP server in PolicyLayer and add a rule for get_learned_voice: 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 Posterly. Nothing to install.
get_learned_voice 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_learned_voice 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_learned_voice. 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_learned_voice is provided by the Posterly MCP server (posterly-mcp-server). 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 →