AI agents call vectorise_list_projects 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 enumerates existing projects without modifying, deleting, or executing anything. List operations are inherently non-destructive reads with minimal risk if exposed to an AI agent. No credentials or sensitive operations appear to be involved beyond accessing metadata about indexed projects.
From the tool's definition Tool name 'vectorise_list_projects' indicates a list operation, which is a read-only query. No description provided, but the naming convention and context of sibling tools (vectorise_search, vectorise_index_status) confirm this is a retrieval operation.
Attacks that exploit this kind of access
vectorise_list_projects. 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_list_projects: 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_list_projects 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_list_projects 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_list_projects. 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_list_projects 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.
vectorise_list_projects is one line of Vectorise's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →