Imagine MCP - install, status & alternatives [2026]

01 · Install Imagine MCP

before you install - you'll need

Set UNDERSTAND_MODELS before connecting. GEMINI_API_KEY, OPENAI_API_KEY are optional or environment-specific per the README.

Claude Code

claude mcp add n24q02m-imagine-mcp -- uvx imagine-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "n24q02m-imagine-mcp": {
      "command": "uvx",
      "args": [
        "imagine-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · container (OCI image) - can be sandboxed away from your filesystem

license Apache-2.0 - declared in the repository

pypi package imagine-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.n24q02m is GitHub-verified and matches the repo owner

03 · What Imagine MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can describe or reason over one or more image/video URLs. media_urls: list[str], prompt: str, provider, tier, max_tokens, and generate an image or video from a text prompt. media_type: image\.

Capability map

Tools grouped from the project's README - what Imagine MCP lets an agent do.

Config

2 tools - e.g. Credential + runtime config: check credential state, set runtime knobs (log level, default provider, TTL), clear response cache.; Framework-injected helper (mcp-core); opens the browser credential form.

config · config__open_relay

Understand

1 tool - e.g. Describe or reason over one or more image/video URLs. media_urls: list[str], prompt: str, provider, tier, max_tokens.

understand

Generate

1 tool - e.g. Generate an image or video from a text prompt. media_type: image\

generate

Help

1 tool - e.g. Full Markdown documentation for understand, generate, or config topics.

help

Latest releases

v1.10.1 · 2026-07-18

v1.10.1 (2026-07-18) · _This release is published under the MIT License._ · Remove redundant orphan-tag shell guard (better-semantic-release @v1 has a built-in one) (#477, d2e7647) · Validate understand passthrough…

v1.10.0 · 2026-07-18

v1.10.0 (2026-07-18) · _This release is published under the MIT License._ · --- · Detailed Changes: v1.10.0-beta.2...v1.10.0

v1.9.0 · 2026-07-14

v1.9.0 (2026-07-14) · _This release is published under the MIT License._ · Lock file maintenance (#451, f1a918f) · Add smithery.yaml for stdio deployment (#454, e30ea9b) · --- · Detailed Changes: v1.9.0-beta.4...v1.9.0

04 · Who maintains Imagine MCP

imagine-mcp is maintained by n24q02m. We track 9 MCP servers from n24q02m - 9 actively maintained, 209 combined GitHub stars, oldest repo from Dec 2025. Full record: all servers from n24q02m.

05 · Facts

repository: github.com/n24q02m/imagine-mcp
category: media - ranked #62 of 155 actively-maintained media servers as of 2026-08-25.
release cadence: 4 releases in the last 90 days (latest 2026-07-18)
registry: io.github.n24q02m/imagine-mcp (active, first published 2026-04-24 · 24 versions)
packages: pypi:imagine-mcp · oci:docker.io/n24q02m/imagine-mcp:latest

06 · Imagine MCP FAQ

Is Imagine MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 4 releases in the last 90 days. We re-verify nightly.

What can Imagine MCP do?

With this server connected, an agent can describe or reason over one or more image/video URLs. media_urls: list[str], prompt: str, provider, tier, max_tokens, and generate an image or video from a text prompt. media_type: image\.

How do I install Imagine MCP?

Run `uvx imagine-mcp`. The README documents 3 environment variables (GEMINI_API_KEY, UNDERSTAND_MODELS, OPENAI_API_KEY) to set first. Set UNDERSTAND_MODELS before connecting. GEMINI_API_KEY, OPENAI_API_KEY are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Imagine MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Imagine MCP

Alternatives to Imagine MCP

Maintained media servers if Imagine MCP isn't the fit.

More media MCP servers · Video Transcriber · Noisy Coding · Glassypic · Tinify AI · Open HCS

More Python MCP servers · Mnemo MCP · Wet MCP · Server Malcolm · WhatsApp MCP Server · Nalegalu MCP · see all