AI agents call vectorise_search to retrieve information from Vectorise without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from a local document index without modifying, deleting, or executing code. Even though the description is empty, the context is clear: a search function on a vector/keyword indexing server performs read-only queries. The tool operates within a local Claude Desktop environment and returns search results without side effects.
From the tool's definition Tool named 'vectorise_search' on a document indexing server; sibling tools indicate this server manages indexed documents for search purposes.
Attacks that exploit this kind of access
vectorise_search. It is categorised as a Read tool in the Vectorise MCP Server, which means it retrieves data without modifying state.
Register the Vectorise MCP server in PolicyLayer and add a rule for vectorise_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 Vectorise. Nothing to install.
vectorise_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 vectorise_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 vectorise_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.
vectorise_search is provided by the Vectorise MCP server (jameslovespancakes/vectorised-embedding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →