AI agents call security_profile to retrieve information from Open Stocks MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'Gets' and the absence of any language indicating mutation, deletion, or execution (e.g., 'updates', 'deletes', 'executes') confirm this is a read-only query. While the tool accesses sensitive user profile information, the read-only nature places it in the Read category.
From the tool's definition Tool name 'security_profile' and description 'Gets security profile and settings' indicate a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access security_profile gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Open Stocks MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for security_profile:
{
"version": "1",
"default": "deny",
"tools": {
"security_profile": {}
}
}security_profile 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.
Gets security profile and settings. It is categorised as a Read tool in the Open Stocks MCP MCP Server, which means it retrieves data without modifying state.
Register the Open Stocks MCP server in PolicyLayer and add a rule for security_profile: 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 Open Stocks MCP. Nothing to install.
security_profile 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 security_profile 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 security_profile. 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.
security_profile is provided by the Open Stocks MCP server (open-agent-tools/open-stocks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Open Stocks MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
152 Open Stocks MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.