AI agents call search_help to retrieve information from Fluent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches documentation, which is a retrieval operation with no side effects. It returns information about help pages and manual sections without modifying any data. The lack of evidence of data modification, deletion, or external execution makes Read the appropriate category. Severity is low because misuse (e.g., searching for sensitive information in docs) has minimal blast radius.
From the tool's definition Tool name 'search_help' combined with server purpose of 'smart URL navigation to ANSYS Fluent documentation' and sibling tool 'list_topics' indicates this retrieves or queries documentation content.
Documented attack patterns abuse exactly the kind of access search_help gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fluent, and nothing reaches the server without passing your rules. This is the rule we recommend for search_help:
{
"version": "1",
"default": "deny",
"tools": {
"search_help": {}
}
}search_help 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.
search_help. It is categorised as a Read tool in the Fluent MCP Server, which means it retrieves data without modifying state.
Register the Fluent MCP server in PolicyLayer and add a rule for search_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 Fluent. Nothing to install.
search_help 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 search_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.
Set action: deny in the PolicyLayer policy for search_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.
search_help is provided by the Fluent MCP server (jiweiqi/fluent-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fluent, 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.
3 Fluent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.