What it does
The MCP Face Transform Server gives MCP clients access to the AceDataCloud Face Transform API. It provides keypoint detection with 90+ landmarks per face, including images with multiple faces; beautification (smoothing, whitening, face slimming and eye enlarging); age transform, which ages or de-ages a portrait; and gender transform, which changes perceived facial gender characteristics. It also offers face swap, which moves a source face onto a target image with an optional asynchronous webhook, cartoonization of portraits, and liveness detection that distinguishes live captures from printed or screen photos. The publisher lists all Face APIs as Alpha.
It suits an MCP-compatible client or agent that needs to call these face-image operations as tools rather than through a direct API integration.
The hosted endpoint supports three connection routes. Hosted OAuth works with clients that support remote MCP OAuth: the user signs in to an AceDataCloud account and approves access, and no token is pasted into the client. A hosted API token is sent as a Bearer header for clients that cannot complete OAuth. A local stdio route runs the mcp-face-transform process on the user's machine and passes an AceDataCloud API token to it. Setup is configured per client, and OAuth and a fixed Authorization header should not be configured together for the same server.
Limitations and requirements
All Face APIs are in Alpha and interfaces may change. Browser sign-in requires an AceDataCloud account. The hosted service can be metered, so current pricing should be checked before running real operations. Token-based access requires an AceDataCloud API key that has access to the required service and a balance that covers requests; a platform account-management token cannot replace it. Keys must be stored privately and never placed in prompts, shared workflows, screenshots or version control. The local stdio route still calls the AceDataCloud API and therefore needs a token. Do not configure both OAuth and a fixed Authorization header for the same server.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 15 Nov 2026 · its page on the source
io.github.AceDataCloud/mcp-face-transform
AceDataCloud Face Transform MCP: keypoints, beautify, age/gender, swap, cartoon, liveness
v2026.11.15.0As shown on registry.modelcontextprotocol.io when we last read it