Low Risk

get_tool_help

Get concise help for Swift tools. Pass tool_name for specific help, or None for all tools.

How to control get_tool_help ↓

AI agents call get_tool_help to retrieve information from SwiftLens without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool fetches informational content (help documentation) about other tools in the SwiftLens server. It has no side effects, makes no modifications to code or system state, and performs no irreversible actions. It is purely a Read operation with minimal security risk.

From the tool's definition Tool description states 'Get concise help for Swift tools' — this retrieves documentation/help text about available tools without modifying code, executing commands, or triggering external operations. It is a lookup/query operation.

Documented attack patterns abuse exactly the kind of access get_tool_help gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and SwiftLens, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tool_help:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_tool_help": {}
  }
}

get_tool_help is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register SwiftLens — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the get_tool_help tool do? +

Get concise help for Swift tools. Pass tool_name for specific help, or None for all tools. It is categorised as a Read tool in the SwiftLens MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_tool_help? +

Register the SwiftLens MCP server in PolicyLayer and add a rule for get_tool_help: 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 SwiftLens. Nothing to install.

What risk level is get_tool_help? +

get_tool_help is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_tool_help? +

Yes. Add a rate_limit block to the get_tool_help 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.

How do I block get_tool_help completely? +

Set action: deny in the PolicyLayer policy for get_tool_help. 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.

What MCP server provides get_tool_help? +

get_tool_help is provided by the SwiftLens MCP server (swiftlens/swiftlens). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SwiftLens tool call.

Deterministic rules across all 15 SwiftLens tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 SwiftLens tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.