// SCAN REPORT

Search

8 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

6 can modify or destroy data

2 read-only

8 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 6 of 8 tools

How to control Search ↓

TOOL MAP

What Search exposes to your agents

Read (2) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Search costs in tokens

1,704 tokens of tool definitions, loaded on every request

0.9% of a 200k context window

382 heaviest tool: browser_type

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Search tools

Execute · High browser_navigate browser_navigate is a browser automation tool that executes navigation commands with side effects that depend on arguments. Execute · High browser_click Clicking UI elements in a browser can trigger a wide range of actions depending on what is clicked — form submissions, purchases, deletions, navigation, downloads, etc. Execute · Low browser_tab_switch This tool triggers an external browser operation (switching active tabs) that affects subsequent browser interactions. Execute · High browser_type This tool executes browser automation actions by typing text or key sequences into focused elements on a live web page.

6 of Search's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Search

PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "browser_close_tabs": {
    "limits": [
      {
        "counter": "browser_close_tabs_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "browser_snapshot": {
    "limits": [
      {
        "counter": "browser_snapshot_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Search — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SEARCH →

Instant setup, no code required.

FULL CATALOGUE

All 8 Search tools

EXECUTE 4 tools

Execute browser_click Click an element by snapshot ref (e.g., 's1e5' for main frame or 's1f2e10' for iframe elements). Returns: (1) Execute browser_navigate Navigate the browser tab: open a URL, move browser history, or create a new tab. Pass 'target' as a URL/domain Execute browser_tab_switch Switch the current browser automation to a different tab by its ID. Get available tab IDs from browser_tabs to Execute browser_type Focus an element by snapshot ref (e.g., 's1e5' for main frame or 's1f2e10' for iframe elements), type text/key

WRITE 2 tools

Write browser_close_tabs Close all tabs in the Jan Browser MCP tab group and ungroup them. This clears the automation session. Use brow Write browser_scroll Scroll the current page or a referenced element; directions: up/down/top/bottom. amount controls pixel distanc

READ 2 tools

Read browser_snapshot Capture an accessibility snapshot of the current tab (ARIA tree, landmarks, headings, ref map). Returns: (1) Y Read browser_tabs Get all tabs in the Jan Browser MCP tab group with their metadata (tabId, url, title, active status). Use this

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Search

How do I prevent bulk modifications through Search? +

The Search server has 2 write tools including browser_close_tabs, browser_scroll. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Search.

How many tools does the Search MCP server expose? +

8 tools across 3 categories: Execute, Read, Write. 2 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Search? +

Register the Search MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Search tool call.

Deterministic rules across all 8 Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SEARCH →

Instant setup, no code required.

8 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.