AI agents call how_to to retrieve information from Proxima without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'how_to' conventionally indicates retrieval of procedural or instructional content, which is a Read operation with minimal risk. The empty description reduces confidence, but the pattern of sibling tools and the query-like name support classification as Read. No evidence of side effects, data modification, code execution, or destructive capability.
From the tool's definition Tool name 'how_to' suggests a query or lookup function returning instructional information. No description provided, limiting certainty.
Documented attack patterns abuse exactly the kind of access how_to gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proxima, and nothing reaches the server without passing your rules. This is the rule we recommend for how_to:
{
"version": "1",
"default": "deny",
"tools": {
"how_to": {}
}
} how_to 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.
how_to. It is categorised as a Read tool in the Proxima MCP Server, which means it retrieves data without modifying state.
Register the Proxima MCP server in PolicyLayer and add a rule for how_to: 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 Proxima. Nothing to install.
how_to 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 how_to 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 how_to. 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.
how_to is provided by the Proxima MCP server (zen4-bit/proxima). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 50 Proxima tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
50 Proxima tools catalogued and risk-classified — across an index of 42,500+ MCP servers.