tancky-ai-image-combiner
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_toolsA | List the Tancky AI photo tools (AI image combiner, couple, family and wedding photos, background remover, upscaler) with links and descriptions. |
| search_guidesA | Find Tancky AI guides about combining, blending and editing photos with AI. Omit query to list all guides. |
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
The two tools target different resource types (product photo tools vs. editorial guides), so their purposes are largely distinct. However, 'list_tools' is easily confused with the MCP meta-convention of listing the server's own tools, which creates a real risk of misselection despite the description clarifying it.
Both names follow a clean verb_noun snake_case pattern (list_tools, search_guides). No mixing of conventions or vague verbs.
Two tools is very thin for a server whose name implies an image-combining capability. There is no tool that actually performs or configures the core function, so the surface feels under-built rather than well-scoped.
The server is named 'tancky-ai-image-combiner' yet offers no tool to combine, blend, or process images — only catalog lookup and guide search. Core lifecycle operations for the stated domain are missing, leaving agents with dead ends for the primary task.