Search documentation for any library, API, or tool. Returns relevant, structured documentation chunks assembled for your specific query. When working with a specific library, always pass the library name for best results.
Risk signalsAccepts freeform code/query input (query)
Part of the Tavily server.
Free to start. No card required.
AI agents call tavily_skill to retrieve information from Tavily 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 tavily_skill 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": {
"tavily_skill": {}
}
}See the full Tavily policy for all 10 tools.
These attack patterns abuse exactly the kind of access tavily_skill 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.
Search documentation for any library, API, or tool. Returns relevant, structured documentation chunks assembled for your specific query. When working with a specific library, always pass the library name for best results.. It is categorised as a Read tool in the Tavily MCP Server, which means it retrieves data without modifying state.
Register the Tavily MCP server in PolicyLayer and add a rule for tavily_skill: 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 Tavily. Nothing to install.
tavily_skill 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 tavily_skill 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 tavily_skill. 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.
tavily_skill is provided by the Tavily MCP server (@modelcontextprotocol/server-tavily). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Tavily 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.