// SCAN REPORT

Third Eye

7 tools. 2 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

2 can modify or destroy data

5 read-only

7 tools total

Community server · catalogue entry verified 30/06/2026

How to control Third Eye ↓

TOOL MAP

What Third Eye exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Third Eye tools

Execute · High screen.record This tool actively records screen activity over time, triggering an ongoing capture operation that monitors and records user screen content. Execute · High screen.scheduled_record This tool triggers an ongoing screen recording operation over time, capturing screen activity continuously.

2 of Third Eye's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Third Eye

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

Cap read operations

{
  "screen.capture": {
    "limits": [
      {
        "counter": "screen.capture_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 Third Eye — 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 THIRD EYE →

Instant setup, no code required.

FULL CATALOGUE

All 7 Third Eye tools

EXECUTE 2 tools

Execute screen.record Record screen with change-based keyframe capture. Captures frames at intervals, discards near-duplicates, and Execute screen.scheduled_record Record screen with scheduled snapshot bursts at specific times. Useful for longer recordings (up to 10 min) to

READ 5 tools

Read screen.capture Capture a full screenshot of the specified display. Returns base64 PNG image with metadata. This is a FREE too Read screen.capture_region Capture a specific region of the screen. Returns base64 PNG image with metadata. This is a FREE tool - you MUS Read screen.get_frame Retrieve a full-resolution frame from a recording. Use recordingId from screen.record response. Specify either Read screen.latest Get the most recently captured screenshot. Returns the last capture with its metadata. This is a FREE tool - y Read screen.list_displays List all available displays/monitors with their properties (index, name, position, dimensions, primary status)

FAQ

Questions about Third Eye

Is the Third Eye MCP server safe to use without restrictions? +

The Third Eye server is primarily read-only with 5 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Third Eye MCP server expose? +

7 tools across 1 categories: Read. 5 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Third Eye? +

Register the Third Eye 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 Third Eye tool call.

Deterministic rules across all 7 Third Eye tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON THIRD EYE →

Instant setup, no code required.

7 Third Eye tools catalogued and risk-classified — across an index of 43,000+ MCP servers.