PhotoFresco is a browser-based raster image editor with layers, masks, selections, adjustments, PSD import/export, and local editing. Its MIT-licensed PhotoFresco Agent connector lets an MCP client or the photofresco CLI operate a browser window on the user's own computer. The public connector source is https://github.com/photofresco/photofresco-agent; installation is currently from the repository rather than a published npm package. A person approves pairing and chooses editing permissions and accessible folders. The connector requires Node.js 22 and a supported Chromium browser. The vendor reports macOS testing, while Windows and Linux are not yet verified. Default MCP discovery exposes a selected set of editing tools; this is a local connector, not a hosted remote MCP API. The core editor is free and ad-supported. The website advertises optional ad-free/cloud storage from $8 per month and separate AI credit packs from $9. Ordinary editor sessions record actions and may upload copies of opened images. The privacy documentation specifically exempts windows opened by the official agent connector from session recording; AI and cloud services still transmit data when used. On-device editing therefore does not mean every access path is entirely offline. Verification covered official guides, pricing and privacy disclosures, the public connector source, CLI help, and MCP initialization exposing 38 default tools with a successful tool-group query. Browser pairing, actual image edits or exports, paid AI, and privacy behavior on the network were not tested.
Best for agent capabilities
Useful in agent tasks
Overview
When to use PhotoFresco
PhotoFresco is listed for Browser workflows. PhotoFresco is a browser-based raster image editor with layers, masks, selections, adjustments, PSD import/export, and local editing. Its MIT-licensed PhotoFresco Agent connector lets an MCP client or the photofresco CLI operate a browser window on the user's own computer. The public connector source is https://github.com/photofresco/photofresco-agent; installation is currently from the repository rather than a published npm package. A person approves pairing and chooses editing permissions and accessible folders. The connector requires Node.js 22 and a supported Chromium browser. The vendor reports macOS testing, while Windows and Linux are not yet verified. Default MCP discovery exposes a selected set of editing tools; this is a local connector, not a hosted remote MCP API. The core editor is free and ad-supported. The website advertises optional ad-free/cloud storage from $8 per month and separate AI credit packs from $9. Ordinary editor sessions record actions and may upload copies of opened images. The privacy documentation specifically exempts windows opened by the official agent connector from session recording; AI and cloud services still transmit data when used. On-device editing therefore does not mean every access path is entirely offline. Verification covered official guides, pricing and privacy disclosures, the public connector source, CLI help, and MCP initialization exposing 38 default tools with a successful tool-group query. Browser pairing, actual image edits or exports, paid AI, and privacy behavior on the network were not tested. Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.
In 4agent's task model, the product maps to browser automation. That makes it a candidate for workflows that research the web.
Integration checklist
- Access: confirm the none authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
- Client support: no SDK is recorded, so verify the HTTP API or another supported integration path.
- Automation: OpenAPI is not currently recorded, MCP is listed as available, and CLI support is listed as available. Confirm each requirement in the provider's current documentation.
- Operations: test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.
Sources and verification
Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.