Vector similarity search for conceptual/fuzzy matching. Use when exact keywords are unknown. DO NOT use for causal
AI agents call vsearch 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.
vsearch is a query/search tool that retrieves data based on vector similarity without creating, modifying, deleting, or executing operations. It falls squarely into the Read category as a data retrieval function. The low severity reflects minimal blast radius—misuse would return potentially irrelevant search results rather than cause system damage or data loss.
From the tool's definition Tool performs 'vector similarity search' for 'conceptual/fuzzy matching', which is a retrieval operation with no data modification, deletion, or execution capabilities. The description explicitly constrains its use to search operations.
Documented attack patterns abuse exactly the kind of access vsearch 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 vsearch:
{
"version": "1",
"default": "deny",
"tools": {
"vsearch": {}
}
}vsearch 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.
Vector similarity search for conceptual/fuzzy matching. Use when exact keywords are unknown. DO NOT use for causal. 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 vsearch: 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.
vsearch 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 vsearch 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 vsearch. 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.
vsearch 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.