---
title: "selfielab"
description: "Generate and edit AI images and videos with the same creative tools as the SelfieLab studio canvas agent."
canonical: https://agentpluginsdirectory.com/plugins/selfielab
last-updated: 2026-11-13
---

# selfielab
Generate and edit AI images and videos with the same creative tools as the SelfieLab studio canvas agent.
## Package we checked
plugin.json sits at the package root in erichie/selfielab-agent-plugin, which is the plugin directory the 1.0.0 spec describes. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 1 skill (creating-with-selfielab) and 1 MCP server (selfielab). Stored mcp.json transports: selfielab streamable-http.
- Slug: selfielab
- Publisher: SelfieLab
- Repository: https://github.com/erichie/selfielab-agent-plugin
- Manifest: plugin.json
- Version: 1.0.0
- Category (editorial): integrations
- Skills: 1 (creating-with-selfielab)
- MCP servers: 1 (selfielab)
- Stars: 0
- Repository created: 2026-08-07
- Repository last pushed: 2026-08-07
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/selfielab
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What selfielab does, in the publisher's words

An Agent Plugin (v1.0.0 spec) that connects compatible agent clients, Codex, ChatGPT, Cursor, GitHub Copilot, Kiro, VS Code, and others, to SelfieLab.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/erichie/selfielab-agent-plugin/HEAD/README.md

## Skills

- creating-with-selfielab: How to generate and edit images and videos with the SelfieLab MCP tools, the async job model, credit costs, reusing existing assets and characters, face-reference etiquette, and the cheaper edit-over-regenerate workflows. Use whenever creating or editing visual media through SelfieLab.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- selfielab: transport: streamable-http; url: https://selfielabstudio.com/api/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.
