retrieval-lens
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 |
|---|---|
| retrieval_observeB | Capture a RAG retrieval run, including query, chunks, scores, sources, and ranks, for later audit and diff workflows. |
| retrieval_queryB | Replay stored retrieval runs so agents can inspect exactly which chunks, scores, sources, and ranks reached the model. |
| retrieval_diffC | Compare two retrieval runs side by side to find missing chunks, shared chunks, and score movement between runs. |
| retrieval_statsB | Aggregate retrieval quality and volume metrics across stored runs, including score distributions, top sources, and daily trends. |
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 4 tools
Each tool addresses a distinct retrieval analysis task: capturing runs (observe), replaying them (query), comparing two runs (diff), and aggregating statistics (stats). No overlaps.
All tools follow a consistent 'retrieval_verb' pattern, making the set predictable and easy to navigate.
Four tools is a concise but complete set for retrieval audit and analysis, covering the essential workflows without unnecessary bloat.
The tools cover the full lifecycle of retrieval evaluation: capture, inspect, compare, and aggregate. No obvious gaps for the stated purpose.