Calculate semantic similarity between two tags using embeddings.
AI agents call tag_similarity 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 computes and returns a similarity score between two tags using pre-computed embeddings. It is purely informational, read-only, and involves no state changes, external operations, or data persistence. The blast radius of misuse is minimal: an agent could make many calls, but each call only returns a numerical similarity metric without affecting the task management system's data or external services.
From the tool's definition Tool 'Calculate semantic similarity between two tags using embeddings' performs a computation that retrieves or queries embedding-based similarity metrics with no side effects—no data is created, modified, or deleted.
Attacks that exploit this kind of access
Calculate semantic similarity between two tags using embeddings. 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_similarity: 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_similarity 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_similarity 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_similarity. 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_similarity 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 →