AI agents call get_saved_content to retrieve information from PersonalizationMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves personal data (saved posts and comments) from platforms without altering or deleting anything. It is fundamentally a Read operation. However, the sensitivity is elevated to 'medium' rather than 'low' because saved content can reveal personal preferences, interests, and behavioral patterns that could enable profiling or social engineering if misused by an unauthorized agent.
From the tool's definition Tool name 'get_saved_content' and description 'Get user's saved posts and comments' indicate retrieval of existing data with no modification or deletion.
Documented attack patterns abuse exactly the kind of access get_saved_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PersonalizationMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_saved_content:
{
"version": "1",
"default": "deny",
"tools": {
"get_saved_content": {}
}
}get_saved_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get user's saved posts and comments. It is categorised as a Read tool in the PersonalizationMCP MCP Server, which means it retrieves data without modifying state.
Register the Personalization MCP server in PolicyLayer and add a rule for get_saved_content: 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 PersonalizationMCP. Nothing to install.
get_saved_content 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_saved_content 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_saved_content. 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_saved_content is provided by the Personalization MCP server (yangliangwei/personalizationmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 PersonalizationMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 PersonalizationMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.