# browser_extract_json

Extract JSON from a matching element on the current page.

Agent View of the PolicyLayer registry record for `browser_extract_json`. HTML page: https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-extract-json

## Facts

- Tool: `browser_extract_json`
- Server: Mcp Captcha Solver (`2captcha/mcp-captcha-solver`) — https://policylayer.com/tools/2captcha-mcp-captcha-solver.md
- Homepage: https://github.com/2captcha/mcp-captcha-solver
- Risk category: Read (Low risk)
- Registry record: grade D, 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": "browser_extract_json",
    "arguments": {}
  }
}
```

## Why browser_extract_json is rated Low

This tool retrieves structured data (JSON) from the current page without modifying, executing, or deleting anything. It has no side effects beyond data retrieval, making it a Read operation with low severity. The blast radius of misuse is limited to information disclosure—an agent could extract unintended data, but cannot damage systems, execute code, or trigger external operations.

From the tool's own definition: "Tool name and description indicate data retrieval: 'Extract JSON from a matching element on the current page.' The verb 'extract' and the lack of any modification language (no create, update, delete, or execute) clearly indicate this is a read-only operation…"

## Use case

AI agents call browser_extract_json to retrieve information from Mcp Captcha Solver 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 Mcp Captcha Solver:

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

## Other tools on Mcp Captcha Solver (12)

- `browser_click` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-click.md
- `browser_click_verify` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-click-verify.md
- `browser_close_page` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-close-page.md
- `browser_close_page_on_error` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-close-page-on-error.md
- `browser_open_page` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-open-page.md
- `captcha_solve_recaptcha_v2` — Execute — https://policylayer.com/tools/2captcha-mcp-captcha-solver/captcha-solve-recaptcha-v2.md
- `browser_extract_text` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-extract-text.md
- `browser_extract_verification_json` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-extract-verification-json.md
- `browser_find_elements` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-find-elements.md
- `browser_get_page_state` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/browser-get-page-state.md
- `healthcheck` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/healthcheck.md
- `list_available_workflows` — Read — https://policylayer.com/tools/2captcha-mcp-captcha-solver/list-available-workflows.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=2captcha-mcp-captcha-solver · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/2captcha-mcp-captcha-solver