Get automation guide for a platform (selectors, URLs, flows, error solutions). Reads from references/ (curated knowledge). Zero cost — only loads when called.
AI agents call platform_guide to retrieve information from ScreenHand without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns reference documentation (selectors, URLs, flows, error solutions) from a static knowledge base. It has no side effects, does not execute code, does not modify data, and does not trigger external operations. It is purely informational and advisory, making it a Read operation with low severity.
From the tool's definition The tool 'reads from references/ (curated knowledge)' and describes itself as providing 'automation guide for a platform' without modifying, executing, or deleting any data.
Documented attack patterns abuse exactly the kind of access platform_guide gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for platform_guide:
{
"version": "1",
"default": "deny",
"tools": {
"platform_guide": {}
}
}platform_guide 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 automation guide for a platform (selectors, URLs, flows, error solutions). Reads from references/ (curated knowledge). Zero cost — only loads when called. It is categorised as a Read tool in the ScreenHand MCP Server, which means it retrieves data without modifying state.
Register the ScreenHand MCP server in PolicyLayer and add a rule for platform_guide: 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 ScreenHand. Nothing to install.
platform_guide 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 platform_guide 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 platform_guide. 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.
platform_guide is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.