Collects your app's logs over HTTP so your agent can search them, follow traces and group errors.
Imagine MCP
agimon-ai · MCP server
Imagine MCP gives an AI assistant two image abilities. It can search Unsplash for stock photos, filtering by orientation and colour and returning image links in full, regular, small and thumbnail sizes with the photographer's name and profile. It can also read an image from a file path, web address or data URI and return its type, size and SHA-256 hash, with base64 data if you ask. Stock search needs an Unsplash access key.
Written by ooruby from the README of @agimon-ai/imagine-mcp 0.30.12.
Not claimed by its maker.
Why it's useful
Your agent can find stock photos with photographer credit and links attached, and check an image's type, size and hash.
What you could do with it
- Ask your agent to find landscape photos on a technology theme and return links in several sizes.
- Search for portrait photos in blue tones and get the photographer credit with each result.
- Have your agent read an image from a file path and report its type, size and hash.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
MCP server for AI image generation and manipulation
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.30.12, the file with digest sha512-zm9OFa+69bbADMZ+wd5u1dWYfpmCUaqxluYjZiDvwxhXAp9l7xIFlJwCxqAHilxMMbOpXeqAMV/HH9qkfLUh8g==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Paste this into your client's MCP configuration.
{
"mcpServers": {
"imagine": {
"command": "npx",
"args": [
"-y",
"@agimon-ai/imagine-mcp@0.30.12"
]
}
}
}Or run it directly.
npx -y @agimon-ai/imagine-mcp@0.30.12Pinned to 0.30.12, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @agimon-ai/imagine-mcp
- Version read
- 0.30.12
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/agimon-ai-imagine-mcp)About this listing
- Kind
- MCP server
- Category
- Content
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-10
More from agimon-ai
See the storefrontLets you choose which MCP servers each Pi session loads, with an allowlist for each work domain.
Runs GitHub Actions workflows on your own Mac, with agent commands and model choices set per step.
Similar MCP servers
All MCP serversProvides a Model Context Protocol server so AI assistants can work with Panda CSS.
Shows PDFs in an interactive viewer your assistant can page through, search, annotate and fill in.
Turns Notion API endpoints into tools your agent can call to search, create and comment on pages.
Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.