Perform a context-aware web search. Optimized for retrieving contextually relevant results.
AI agents call searchContext to retrieve information from MCP Tavily without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from the web without modifying, deleting, or executing anything. It falls squarely under the Read category as a search operation that has no side effects beyond fetching and returning data. The low severity reflects minimal risk even if misused by an agent—web searches cannot damage systems or trigger financial consequences.
From the tool's definition Tool name 'searchContext' combined with description 'Perform a context-aware web search. Optimized for retrieving contextually relevant results' indicates a query/retrieval operation with no data modification or execution capabilities.
Documented attack patterns abuse exactly the kind of access searchContext gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Tavily, and nothing reaches the server without passing your rules. This is the rule we recommend for searchContext:
{
"version": "1",
"default": "deny",
"tools": {
"searchContext": {}
}
}searchContext 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.
Perform a context-aware web search. Optimized for retrieving contextually relevant results. It is categorised as a Read tool in the MCP Tavily MCP Server, which means it retrieves data without modifying state.
Register the MCP Tavily MCP server in PolicyLayer and add a rule for searchContext: 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 MCP Tavily. Nothing to install.
searchContext 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 searchContext 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 searchContext. 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.
searchContext is provided by the MCP Tavily MCP server (kshern/mcp-tavily). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Tavily, 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.
4 MCP Tavily tools catalogued and risk-classified — across an index of 43,000+ MCP servers.