AI agents call vectorise_list_jobs 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 and displays status information about past and current indexing jobs within the server's session memory. It performs a query operation only, making no modifications to data or triggering external operations. The low severity reflects the minimal risk of misuse—listing jobs cannot corrupt documents, delete projects, or cause system damage.
From the tool's definition Tool name is 'vectorise_list_jobs' and description states 'List indexing jobs from this server session'. The verb 'list' is explicitly a retrieval operation with no side effects.
Attacks that exploit this kind of access
List indexing jobs from this server session (resets on restart). 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_jobs: 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_jobs 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_jobs 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_jobs. 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_jobs 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 →