AI agents call contextual_keyword_search to retrieve information from Search Tools MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information from repositories based on keywords. It retrieves or queries data without producing side effects, reversible modifications, code execution, destructive actions, or financial impacts. The 'keyword search' semantic and positioning among other analysis tools on this server (which are all read-only analyses) confirm it is a Read operation.
From the tool's definition Tool name 'contextual_keyword_search' combined with server description stating it performs 'context-aware keyword searches with importance-ranked results'.
Documented attack patterns abuse exactly the kind of access contextual_keyword_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search Tools MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for contextual_keyword_search:
{
"version": "1",
"default": "deny",
"tools": {
"contextual_keyword_search": {}
}
}contextual_keyword_search 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.
contextual_keyword_search. It is categorised as a Read tool in the Search Tools MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Search Tools MCP Server MCP server in PolicyLayer and add a rule for contextual_keyword_search: 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 Search Tools MCP Server. Nothing to install.
contextual_keyword_search 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 contextual_keyword_search 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 contextual_keyword_search. 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.
contextual_keyword_search is provided by the Search Tools MCP Server MCP server (voxmenthe/search-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Search Tools MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Search Tools MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.