# vector_search

Perform a vector similarity search on the Azure AI Search index.

Agent View of the PolicyLayer registry record for `vector_search`. HTML page: https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main/vector-search

## Facts

- Tool: `vector_search`
- Server: Azure AI Agent Service + Azure AI Search MCP Server (`0lovesakura0/mcp-server-azure-ai-agents-main`) — https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main.md
- Homepage: https://github.com/0lovesakura0/mcp-server-azure-ai-agents-main
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "vector_search",
    "arguments": {}
  }
}
```

## Why vector_search is rated Low

Vector search queries a pre-built index to retrieve semantically similar documents based on embedding similarity. This is a passive data retrieval operation with no side effects, no data modification, no code execution, and no financial impact. The primary risk is information disclosure if sensitive documents are indexed, but the tool itself is a standard read operation.

From the tool's own definition: "Tool performs 'vector similarity search' on an index, returning matching documents without modifying, creating, or deleting data. The verb 'search' and description explicitly indicate read-only retrieval."

## Use case

AI agents call vector_search to retrieve information from Azure AI Agent Service + Azure AI Search MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Azure AI Agent Service + Azure AI Search MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "vector_search": {}
  }
}
```

## Other tools on Azure AI Agent Service + Azure AI Search MCP Server (4)

- `hybrid_search` — Read — https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main/hybrid-search.md
- `keyword_search` — Read — https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main/keyword-search.md
- `search_index` — Read — https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main/search-index.md
- `web_search` — Read — https://policylayer.com/tools/0lovesakura0-mcp-server-azure-ai-agents-main/web-search.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0lovesakura0-mcp-server-azure-ai-agents-main · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0lovesakura0-mcp-server-azure-ai-agents-main