semantic_search

Search Zakar for memories semantically related to a query. Returns the most relevant thoughts ranked by cosine similarity.

Server Zakar tkbrannon/zakar
Category Read
Risk class Low
Parameters 00 required

What semantic_search does on Zakar

AI agents call semantic_search to retrieve information from Zakar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why semantic_search needs a policy

This tool retrieves and queries data (searching a memory store) without side effects. It is a read-only operation that returns ranked results based on semantic similarity. No data is created, modified, deleted, or executed. The blast radius of misuse is low—an agent could retrieve sensitive memories but cannot alter or destroy data, trigger external actions, or commit financial obligations.

From the tool's definition The tool 'semantic_search' is described as returning 'the most relevant thoughts ranked by cosine similarity' in response to a query. It performs a search and retrieval operation with no modification, creation, or deletion of data.

Questions about semantic_search

What does the semantic_search tool do? +

Search Zakar for memories semantically related to a query. Returns the most relevant thoughts ranked by cosine similarity. It is categorised as a Read tool in the Zakar MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on semantic_search? +

Register the Zakar 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 Zakar. Nothing to install.

What risk level is semantic_search? +

semantic_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit semantic_search? +

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.

How do I block semantic_search completely? +

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.

What MCP server provides semantic_search? +

semantic_search is provided by the Zakar MCP server (tkbrannon/zakar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

semantic_search is one line of Zakar'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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.