Search for passages by meaning using semantic similarity.
AI agents call semantic_search to retrieve information from Mcp Zotero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Semantic search is a read-only operation that retrieves information based on similarity matching. It queries local embeddings to find passages but does not create, modify, delete, or execute code. The blast radius of misuse is minimal—an attacker might extract sensitive information from a user's Zotero library, but cannot alter or destroy data. This falls clearly under the Read category.
From the tool's definition Tool name: 'semantic_search' with description: 'Search for passages by meaning using semantic similarity.' This performs a query operation across stored embeddings to retrieve matching content based on semantic meaning, with no modification or deletion of…
Attacks that exploit this kind of access
Search for passages by meaning using semantic similarity. It is categorised as a Read tool in the Mcp Zotero MCP Server, which means it retrieves data without modifying state.
Register the Mcp Zotero MCP server in PolicyLayer and add a rule for semantic_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 Mcp Zotero. Nothing to install.
semantic_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 semantic_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 semantic_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.
semantic_search is provided by the Mcp Zotero MCP server (nealcaren/mcp-zotero). 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 →