AI agents call keyword_search to retrieve information from Weaviate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Keyword search retrieves and queries data from a vector database without modifying, deleting, or executing arbitrary code. It is a passive read operation with no side effects. While the description field is empty, the server's documented purpose and sibling tools provide strong context that this is a search/retrieval function.
From the tool's definition Tool name 'keyword_search' combined with server context showing 'keyword...search across local or cloud instances.' The tool is grouped with other search operations (hybrid_search, semantic_search, search) which are all read-only query operations.
Documented attack patterns abuse exactly the kind of access keyword_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Weaviate MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for keyword_search:
{
"version": "1",
"default": "deny",
"tools": {
"keyword_search": {}
}
}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.
keyword_search. It is categorised as a Read tool in the Weaviate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weaviate MCP Server MCP server in PolicyLayer and add a rule for 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 Weaviate MCP Server. Nothing to install.
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 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 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.
keyword_search is provided by the Weaviate MCP Server MCP server (sajal2692/mcp-weaviate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Weaviate MCP Server, 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.
11 Weaviate MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.