upscale_image
imagepeek: Upscale a small image 2x with a neural model. Returns creates a 2x neural derivative of one PNG, JPEG or WebP using offline QuickSRNet Small (BSD-3-Clause). Neural x2 derivative, not recovered detail or OCR. PNG/JPEG/WebP <=250000 pixels, 2048 per side; output PNG <=1 MP. EXIF oriented...
This record as markdown: /tools/dev-tanod-tanod/upscale-image.md
What upscale_image does on Tanod
AI agents call upscale_image to retrieve information from Tanod without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | object | — | Public http(s) URL of the image (at most 10 MB; private, internal and IP-literal hosts are refused); or use image_base64. |
output | string | — | base64 (default): inline. url: stored for 24 hours; link, metadata. |
image_base64 | object | — | The image as standard or url-safe base64 (at most 10 MB decoded; a data:image/...;base64, prefix is fine); or use url. |
Parameters from the server's own tool schema.
Why upscale_image is rated Low
Even though upscale_image only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs upscale_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tanod, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For upscale_image, this is the rule to start with:
upscale_image is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Tanod, apply this rule, and every upscale_image call is checked against it from then on.
Questions about upscale_image
imagepeek: Upscale a small image 2x with a neural model. Returns creates a 2x neural derivative of one PNG, JPEG or WebP using offline QuickSRNet Small (BSD-3-Clause). Neural x2 derivative, not recovered detail or OCR. PNG/JPEG/WebP <=250000 pixels, 2048 per side; output PNG <=1 MP. EXIF oriented, alpha white, frame 0. Failures not charged.. Up to 45 s. Price: USD 0.01. No free tier. It is categorised as a Read tool in the Tanod MCP Server, which means it retrieves data without modifying state.
upscale_image accepts 3 parameters: url, output, image_base64. The full parameter table on this page comes from the server's own tool schema.
Register the Tanod MCP server in PolicyLayer and add a rule for upscale_image: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tanod. Nothing to install.
upscale_image is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the upscale_image rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for upscale_image. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
upscale_image is provided by the Tanod MCP server (https://tanod.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tanod, and thousands of servers like it.
This server
Across the catalogue