Image Edit MCP Server

Chat with AI and run tools instantly.

Deterministic pixel editing — crop, exposure, saturation, sharpen, resize, and format convert. Host passes image bytes; tool returns edited bytes.

Chat with AI

Managed

7 tools

Agent guide included

Chat with AI and run tools instantly.

Browse all tools

AI Skill
SKILL.md

Domain knowledge for Image Edit — workflow patterns, data models, and gotchas for your AI agent.

Image Edit

Deterministic pixel editor. The MCP host reads local image files and passes file_name + content_base64; tools return output_file_name + content_base64 for the host to write. No Desktop proxy.

Primary tools

apply_edit_pipeline — ordered JSON ops; returns edited bytes
apply_pipeline_from_yaml — same pipeline from YAML (operations, pipeline, or ops list)
get_image_info — width, height, format, byte size from image bytes
crop_image, modulate_image, sharpen_image, convert_image — single-op shortcuts

Pipeline op schema

operations: - op: crop aspect: "16:9" gravity: center - op: modulate brightness: 1.05 saturation: 0.92 - op: sharpen sigma: 0.8

Supported ops: crop, modulate, sharpen, resize, convert.

Bytes contract

file_name is a logical filename with extension (format hint only; not a server-side path)
output_file_name defaults to file_name when omitted
Max decoded image size: 50 MB

Tools in this Server (7)

Apply Edit Pipeline

Apply deterministic pixel ops (crop, modulate, sharpen, resize, convert) to image bytes. Returns output_file_name and content_base64 for the host to w...

Apply Pipeline From YAML

Apply a YAML-defined edit pipeline to image bytes. Returns output_file_name and content_base64 for the host to write.

Convert Image

Apply a single convert op to image bytes. Prefer apply_edit_pipeline for multi-step chains.

Crop Image

Apply a single crop op to image bytes. Prefer apply_edit_pipeline for multi-step chains.

Get Image Info

Return width, height, format, and byte size for image bytes. Pass file_name + content_base64 after the host reads a local file.

Modulate Image

Apply a single modulate op to image bytes. Prefer apply_edit_pipeline for multi-step chains.

Sharpen Image

Apply a single sharpen op to image bytes. Prefer apply_edit_pipeline for multi-step chains.

Frequently Asked Questions

What is the Image Edit MCP server?

Deterministic pixel editing — crop, exposure, saturation, sharpen, resize, and format convert. Host passes image bytes; tool returns edited bytes. It provides 7 tools that AI agents can use through the Model Context Protocol (MCP).

How do I connect Image Edit to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/image-edit. Authentication is handled automatically.

How many tools does Image Edit provide?

Image Edit provides 7 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Image Edit require?

Image Edit uses open data APIs — no authentication required.

Setup Instructions

Connect Image Edit to any MCP client in minutes

MCP URL

https://mcp.mcpbundles.com/bundle/image-edit

Claude.ai Cursor VS Code VS Code Insiders Goose LM Studio Cherry Studio ChatGPT

One-click install:

Install on Claude.ai Install for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

Open claude.ai → Settings → Connectors.
Click the + button and choose Add custom connector.
Set Name to Image Edit and paste the MCP URL into Remote MCP server URL.
Click Add. Image Edit will appear under Not connected — select it and click Connect to complete OAuth.