# retrieval-lens

> Use this tool when you need to audit and analyze the retrieval process of MCP agents, as it logs and records model interactions, scores, sources, and rankings for later review and comparison. It solves problems related to understanding and optimizing model performance, allowing for replay and diffing of retrieval runs. The retrieval-lens tool takes in model interactions as input and outputs a log of retrieval events for post-hoc analysis.

Canonical page: https://skillsregistry.net/skills/vbj1808-retrieval-lens  
JSON: https://api.skillsregistry.net/v1/skills/vbj1808-retrieval-lens

## Description

A black-box flight recorder for RAG retrieval inside MCP agents. Logs what chunks the model saw, scores, sources, and rankings - so you can audit, replay, and diff retrieval runs after the fact.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x85ypw6vw8)
- **Repository:** <https://github.com/Vbj1808/retrieval-lens>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "vbj1808-retrieval-lens"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vbj1808-retrieval-lens` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vbj1808-retrieval-lens/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt