AI agents call kg_query to retrieve information from ClawMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or searches existing data from the knowledge graph without creating, modifying, deleting, or executing external operations. Querying a knowledge graph for entity information is a foundational read operation with minimal security risk—misuse would only expose existing information already stored in the system.
From the tool's definition Tool name 'kg_query' and description 'Query the knowledge graph for an entity' indicate a read-only operation. The verb 'query' combined with 'knowledge graph' suggests data retrieval without modification.
Documented attack patterns abuse exactly the kind of access kg_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for kg_query:
{
"version": "1",
"default": "deny",
"tools": {
"kg_query": {}
}
} kg_query 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.
Query the knowledge graph for an entity. It is categorised as a Read tool in the ClawMem MCP Server, which means it retrieves data without modifying state.
Register the ClawMem MCP server in PolicyLayer and add a rule for kg_query: 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 ClawMem. Nothing to install.
kg_query 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 kg_query 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 kg_query. 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.
kg_query is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.