find-images-mcp-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHAT_WORKING_DIRECTORIES | Yes | Absolute base directory for all Bionic scratchpads. Example: /Users/ceveyne/.lmstudio/scratchpads | |
| FIND_IMAGES_MCP_INDEXER_URL | Yes | Base URL of the image server. Example: https://127.0.0.1:9760/mcp | |
| FIND_IMAGES_MCP_INDEXER_TOKEN | Yes | Bearer token for the image server. Example: b2f4b1e2-3g0w-4c8t-3b7q-6n2b5b7x1a9d | |
| FIND_IMAGES_MCP_INDEXER_CA_CERT | No | 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 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_imageB | Find visually similar and metadata-related images. Use this tool for cross-modal retrieval over images from several sources across the local network. |
| tag_imageB | Manage persistent tags for indexed images through the configured image server. Examples:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
find_image handles retrieval, tag_image handles tag management—two clearly distinct purposes with no overlap. Even though tag_image uses sub-actions, the tool boundary against find_image is unambiguous.
Both tools follow a clean verb_noun snake_case pattern (find_image, tag_image). Fully consistent.
Two tools is thin for an image bridge that claims cross-modal retrieval and tag management. It's borderline; the surface earns its place but feels minimal.
Only find and tag operations exist. Missing obvious lifecycle operations like indexing new images, listing indexed images, retrieving image metadata/details, or listing/querying existing tags—significant gaps for a retrieval bridge.