Find AI tools that match a natural-language user need. Parameters ---------- description : str The user's need in their own words. Be specific about the scenario, audience, platform, language and budget when known. Examples: '我是新手想学编程，要免费的 AI 工具'; 'I need an AI to generate a 10-page PPT from an o...
Part of the Trueai server.
Free to start. No card required.
AI agents call recommend_ai_tools to retrieve information from Trueai without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though recommend_ai_tools only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"recommend_ai_tools": {}
}
}See the full Trueai policy for all 4 tools.
These attack patterns abuse exactly the kind of access recommend_ai_tools gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Find AI tools that match a natural-language user need. Parameters ---------- description : str The user's need in their own words. Be specific about the scenario, audience, platform, language and budget when known. Examples: '我是新手想学编程，要免费的 AI 工具'; 'I need an AI to generate a 10-page PPT from an outline'. top_k : int (1-10, default 5) Maximum number of candidates to return. Returns ------- JSON: {intents, candidates, external}. candidates is already ranked by relevance & score. external lists fallback nav sites only when no in-catalog candidate matches.. It is categorised as a Read tool in the Trueai MCP Server, which means it retrieves data without modifying state.
Register the Trueai MCP server in PolicyLayer and add a rule for recommend_ai_tools: 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 Trueai. Nothing to install.
recommend_ai_tools 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 recommend_ai_tools 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 recommend_ai_tools. 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.
recommend_ai_tools is provided by the Trueai MCP server (https://www.shiflowai.cloud/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Trueai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.