Get IDF weights for all tags (simplified for ranking).
AI agents call tag_weights to retrieve information from Vector Task MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed IDF (Inverse Document Frequency) weights for ranking purposes. It performs a read-only query of existing statistical data without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could only access ranking metadata, not modify tasks or trigger external actions.
From the tool's definition Tool name 'tag_weights' and description 'Get IDF weights for all tags (simplified for ranking)' indicate a retrieval operation.
Attacks that exploit this kind of access
Get IDF weights for all tags (simplified for ranking). It is categorised as a Read tool in the Vector Task MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vector Task MCP Server MCP server in PolicyLayer and add a rule for tag_weights: 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 Vector Task MCP Server. Nothing to install.
tag_weights 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 tag_weights 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 tag_weights. 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.
tag_weights is provided by the Vector Task MCP Server MCP server (xsaven/vector-task-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 →