// SCAN REPORT

Bedrock Image

20 tools. 19 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

19 can modify or destroy data

1 read-only

20 tools total

Community server · catalogue entry verified 02/07/2026

How to control Bedrock Image ↓

TOOL MAP

What Bedrock Image exposes to your agents

Read (1) Write / Execute (18) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Bedrock Image tools

Financial · Critical style_transfer style_transfer Execute · Medium remove_object Based on the server context (image generation/editing via Amazon Bedrock) and sibling tools (inpaint_image, outpaint_image, remove_background, search_and_recolor), remove_object likely performs an image editing operation Execute · Medium transform_image_sd35 Image transformation is an Execute operation—it triggers external ML service operations (Stable Diffusion) whose effects depend on input arguments (image, transformation parameters). Execute · Medium sketch_to_image The description is empty, so classification relies on the tool name and server context.

19 of Bedrock Image's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Bedrock Image

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

Block financial tools by default

{
  "style_transfer": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "create_ellipse_mask": {
    "limits": [
      {
        "counter": "create_ellipse_mask_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "search_and_replace": {
    "limits": [
      {
        "counter": "search_and_replace_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 Bedrock Image — 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 BEDROCK IMAGE →

Instant setup, no code required.

FULL CATALOGUE

All 20 Bedrock Image tools

FINANCIAL 1 tools

Financial style_transfer style_transfer

EXECUTE 6 tools

Execute remove_object remove_object Execute sketch_to_image sketch_to_image Execute transform_image_sd35 transform_image_sd35 Execute upscale_conservative upscale_conservative Execute upscale_creative upscale_creative Execute upscale_fast upscale_fast

WRITE 12 tools

Write create_ellipse_mask create_ellipse_mask Write create_full_mask create_full_mask Write create_rectangular_mask create_rectangular_mask Write generate_image generate_image Write generate_image_sd35 generate_image_sd35 Write generate_image_with_colors generate_image_with_colors Write inpaint_image inpaint_image Write outpaint_image outpaint_image Write remove_background remove_background Write search_and_recolor search_and_recolor Write structure_control structure_control Write style_guide style_guide

READ 1 tools

Read search_and_replace search_and_replace

EXPLORE

Related servers

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

FAQ

Questions about Bedrock Image

Can an AI agent move money through the Bedrock Image MCP server? +

Yes. The Bedrock Image server exposes 1 financial tools including style_transfer. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Bedrock Image? +

The Bedrock Image server has 12 write tools including create_ellipse_mask, create_full_mask, create_rectangular_mask. 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 Bedrock Image.

How many tools does the Bedrock Image MCP server expose? +

20 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 1 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on Bedrock Image? +

Register the Bedrock Image 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 Bedrock Image tool call.

Deterministic rules across all 20 Bedrock Image tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON BEDROCK IMAGE →

Instant setup, no code required.

20 Bedrock Image tools catalogued and risk-classified — across an index of 43,000+ MCP servers.