Imagine Mcp
A production-grade bridge to image and video understanding plus generation across Gemini, OpenAI, and Grok. You get two core tools: `understand` for reasoning over image and video URLs with configurable context length, and `generate` for text-to-image, image-to-image, and text-to-video workflows. Each provider exposes "poor" and "rich" tiers so you can trade speed for quality on the fly. The server ranks models weekly against Artificial Analysis and LMArena leaderboards, caches responses to disk with configurable TTL, and degrades gracefully when credentials are missing. Ships with stdio and HTTP transports, plus a config tool that surfaces relay forms, credential state checks, and runtime knobs like log level and default provider. Reach for this when you need multimodal ops without hardcoding a single provider.
- GitHub stars
- 4
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env vars
- 4
- last updated
- Sep 12, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
understandDescribe or reason over one or more image/video URLs.
Describe or reason over one or more image/video URLs.
No parameter schema in public metadata yet.
generateGenerate an image or video from a text prompt.
Generate an image or video from a text prompt.
No parameter schema in public metadata yet.
configCredential and runtime config: check credential state, set runtime knobs, clear response cache.
Credential and runtime config: check credential state, set runtime knobs, clear response cache.
No parameter schema in public metadata yet.
helpFull Markdown documentation for understand, generate, or config topics.
Full Markdown documentation for understand, generate, or config topics.
No parameter schema in public metadata yet.
config__open_relayFramework-injected helper (mcp-core); opens the browser credential form.
Framework-injected helper (mcp-core); opens the browser credential form.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
UNDERSTAND_MODELSOrdered model chain for the understand path 'provider/model,...' (order = litellm fallback; provider inferred from the prefix). Empty = understand off (provider/tier catalog default). Generation stays provider/tier native.
GEMINI_API_KEYsecretGoogle AI Studio API key (aistudio.google.com/apikey)
OPENAI_API_KEYsecretOpenAI API key (platform.openai.com)
XAI_API_KEYsecretxAI (Grok) API key (console.x.ai)
Readme
ARCHIVED 2026-09-13 — This repository is no longer maintained. Use your image provider's native API instead of this MCP server. Existing installations keep working but receive no updates or support.
imagine-mcp
mcp-name: io.github.n24q02m/imagine-mcp
Image and video understanding + generation for AI agents -- across Gemini, OpenAI, and Grok.
Details
- Repository
- github.com/n24q02m/imagine-mcp
- Categories
- AI & LLM Tools, Media & Entertainment
- Package
imagine-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from n24q02m
Related AI & LLM Tools MCP servers
View all
Acmi Mcpmadezmedia/acmiPersistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis.3stars
Logic Serverauctalis/nocturnusaiAgent reasoning, memory, and token-optimized context for AI applications.2stars
Contextforge Mcpalfredoizdev/contextforge-mcpPersistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.2stars
Purmemopurmemo-ai/purmemo-mcpAI memory across Claude, ChatGPT, Gemini, and Cursor. Save, search, and recall context everywhere.2stars
Gemot Deliberation Serverjustinstimatze/gemotDeliberation primitive for multi-agent coordination: cruxes, vote clustering, consensus.2stars