imagine-mcp 1.2.0b1

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

imagine-mcp

mcp-name: io.github.n24q02m/imagine-mcp

Production-grade MCP server for image and video understanding + generation across Gemini, OpenAI, and Grok.

Features

• Multimodal understanding -- Describe, classify, or reason over images and videos (Gemini handles mixed image + video in one call)
• Image generation -- Text-to-image and image-to-image (edit / inpaint) across Gemini Imagen, OpenAI gpt-image, Grok Imagine
• Video generation -- Text-to-video and image-to-video (Gemini Veo 3.1, Grok Imagine Video)
• 3 providers x 2 tiers -- Same interface for gemini / openai / grok at poor (cheap/fast) or rich (high quality); swap via parameter
• Leaderboard-ranked models -- Provider ordering auto-refreshed weekly from Artificial Analysis + LMArena leaderboards
• Zero-config onboarding -- Browser-based credential relay form; no .env files or manual credential plumbing
• Degraded mode -- Server starts with zero credentials and surfaces remaining providers as you add keys
• Response cache -- Disk-based caching of understand responses with configurable TTL
• Smart stdio proxy -- stdio transport spawns a local HTTP daemon and forwards JSON-RPC frames, sharing credentials across invocations

Setup

With AI Agent -- copy and send this to your AI agent:

Please set up imagine-mcp for me. Follow this guide: https://raw.githubusercontent.com/n24q02m/imagine-mcp/main/docs/setup-with-agent.md

Manual setup -- follow docs/setup-manual.md

Tools

Tool	Actions	Description
understand	--	Describe or reason over one or more image/video URLs. media_urls: list[str], prompt: str, provider, tier, max_tokens.
generate	--	Generate an image or video from a text prompt. media_type: image|video, optional reference_image_url, optional job_id (video poll), aspect_ratio, duration_seconds.
config	open_relay, relay_status, relay_skip, relay_reset, relay_complete, warmup, status, set, cache_clear	Credential + runtime config: open relay form, check credential state, set runtime knobs (log level, default provider, TTL), clear response cache.
help	--	Full Markdown documentation for understand, generate, or config topics.

Model IDs per provider x action x tier are leaderboard-ranked; see docs/models.md (auto-regenerated from src/imagine_mcp/models.py).

Security

• SSRF + LFI prevention -- All media_urls and reference_image_url are validated at the dispatch boundary; only http:// and https:// schemes reach the providers. file://, ftp://, gopher://, and scheme-less URLs are rejected.
• No credentials in errors -- Provider-side errors are sanitized before being returned.
• Degraded start -- Missing credentials do not prevent the server from starting; affected actions surface actionable errors instead of crashing at boot.
• Relay transport -- Credentials submitted through the local relay form are stored encrypted via mcp-core (config.enc, user-scoped platformdirs).

Build from Source

git clone https://github.com/n24q02m/imagine-mcp.git
cd imagine-mcp
mise run setup      # or: uv sync --group dev
mise run dev        # run http local relay daemon

Contributing

See CONTRIBUTING.md for the full development workflow, commit convention, and release process. Issues + Discussions welcome.

License

MIT -- see LICENSE.