find-images-mcp-bridge
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@find-images-mcp-bridgefind images of a red car on a highway"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
find-images-mcp-bridge
Local stdio MCP bridge between LM Studio Bionic and a Find Images.app MCP server. Provides next-level image search and information retrieval based on multimodal embeddings.
The bridge exposes find_image and tag_image tools to Bionic. It forwards search and tag requests to the Find Images MCP server, downloads its previews, writes them to the specified scratchpad, and registers them for later editing or processing.
Prerequisites
macOS 26 or later on Apple Silicon.
Find Images.app version
0.1.56-1or later, fully set up and verified to find images.Bionic Version 1.1.4+3 or later.
Related MCP server: LM Studio MCP Bridge
Bionic Configuration
The stdio definition requires these values:
command: nodeargs: path to the find-images-mcp-bridge'sindex.js. Example:/Users/ceveyne/.lmstudio/extensions/plugins/ceveyne/find-images-mcp-bridge/dist/index.jsCHAT_WORKING_DIRECTORIES: absolute base directory for all Bionic scratchpads. Example:/Users/ceveyne/.lmstudio/scratchpadsFIND_IMAGES_MCP_INDEXER_URL: base URL of the image server. Example:https://127.0.0.1:9760/mcpFIND_IMAGES_MCP_INDEXER_TOKEN: bearer token for the image server. Example:b2f4b1e2-3g0w-4c8t-3b7q-6n2b5b7x1a9dFIND_IMAGES_MCP_INDEXER_CA_CERT: optional path to the image server's self-signed CA/server certificate; standard certificate validation remains active without this value. Example:/Users/ceveyne/.find-images/server/server.crt
{
"name": "find-images",
"enabled": true,
"connection": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/find-images-mcp-bridge/dist/index.js"],
"cwd": "/absolute/path/to/bionic-scratchpads",
"env": {
"CHAT_WORKING_DIRECTORIES": "/absolute/path/to/bionic-scratchpads",
"FIND_IMAGES_MCP_INDEXER_URL": "https://find-images-server.example.com/mcp",
"FIND_IMAGES_MCP_INDEXER_TOKEN": "<bearer-token>",
"FIND_IMAGES_MCP_INDEXER_CA_CERT": "/absolute/path/to/server.crt"
}
}
}Setup step by step
Download and install the Find Images.app. Using the latest available version is highly recommended.
Run the guided Onboarding and verify you're set up according to the Find Images.app README.
Enter Find Images General Settings and add a bearer token to the "MCP Server Bearer Token" field. This is required to get the MCP server started.
cd ~/.lmstudio/extensions/plugins/ceveyne && git clone https://github.com/ceveyne/find-images-mcp-bridgecd ~/.lmstudio/extensions/plugins/ceveyne/find-images-mcp-bridge && npm run buildStart Bionic > Settings > MCP > Add custom MCP. Configuration:
Name: find-images
Connection: On this computer
Command: node
Enter Advanced settings according to your setup, following the "Bionic Configuration" examples above.
Save your Settings and make sure the Status is
Connected • 2 tools ready.Ask your Bionic agent to find images.
Text your friends about your gorgeous* Find Images setup.
* May or may not be gorgeous – depending on your settings.
Companion plugin
For LM Studio, use the LM Studio plugin: find-image. To generate images, use the LM Studio plugin – made for Bionic: generate-image.
Development
npm run build
npm testLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Related MCP Servers
- FlicenseDqualityDmaintenanceEnables seamless integration between MCP-compatible clients (like LM Studio) and Google Gemini API for image generation and multimodal tasks. Provides a hybrid local-cloud workflow combining local LM Studio execution with Gemini's cloud-powered image generation capabilities.13-
- FlicenseCqualityDmaintenanceEnables MCP clients to interact with local LLMs via LM Studio, supporting dynamic chat, vision, RAG, file interaction, and model orchestration.28-
- FlicenseNot gradedqualityCmaintenanceEnables AI clients like Claude to understand, analyze, and describe local images via VL models through the MCP protocol.-
- FlicenseNot gradedqualityDmaintenanceEnables semantic image search using CLIP embeddings and visual question answering through MCP tools, allowing natural language interaction with images.-