loop-improver-mcp
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| compare_loopsC | Compare repositories against README/Copilot/objectives/agents/insights loop architecture. |
| improve_loopC | Install or refresh the foundational loop architecture in a target repository. |
| record_loop_insightC | Write the current architecture insight to .github/insights/loop-improver-mcp.md. |
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 3 tools
Each tool has a distinct purpose: comparing repositories, installing/refreshing architecture, and recording insights. No overlap.
All tools follow a consistent verb_noun pattern (compare_loops, improve_loop, record_loop_insight).
3 tools is on the lower end but well-scoped for the narrow domain of loop architecture management. Not too few to be useless.
Covers the core workflow of comparing, improving, and recording insights. Minor gaps like deletion or listing are not essential for the stated purpose.