mcp-proxy-quality-report

mcp-proxy-quality-report is a command for Claude Code from zach-source/mcp-rust-proxy. It costs 9 tokens per session (143 once invoked), scanned A, original, MIT.

A command that reports how well different context sources perform based on quality feedback.

In plain words
What is it for?
Use it to view feedback trends, top and low-performing contexts, and suggested updates.
Why use it?
It helps identify useful context, declining results, and context that may need review or removal.

Command for Claude Code

Part of the mcp-proxy-tracing plugin — 13 commands, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/zach-source/mcp-rust-proxy/mcp-proxy-quality-report
Clone the repo
git clone --depth 1 https://github.com/zach-source/mcp-rust-proxy

Made for: Claude Code.

Or install mcp-proxy-tracing, the plugin that ships this one along with the rest of its 13 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-proxy-quality-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/zach-source/mcp-rust-proxy/mcp-proxy-quality-report.svg)](https://agentmods.dev/commands/zach-source/mcp-rust-proxy/mcp-proxy-quality-report)
Your own site
<a href="https://agentmods.dev/commands/zach-source/mcp-rust-proxy/mcp-proxy-quality-report"><img src="https://agentmods.dev/badge/commands/zach-source/mcp-rust-proxy/mcp-proxy-quality-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00143
Opus 5 $0.00005 $0.00072
Sonnet 5 $0.00002 $0.00029
Haiku 4.5 $0.00001 $0.00014

Measured 4d ago against content hash 65c5d68ea2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-proxy-quality-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/commands/mcp-proxy-quality-report.md · 19 lines

What it actually says

Generate a quality report showing context performance metrics.

Instructions for Claude:

  1. Read trace://quality/recent-feedback resource
  2. Read trace://quality/top-contexts resource (when available)
  3. Read trace://quality/deprecated-contexts resource (when available)
  4. Query the database for aggregate statistics
  5. Present a formatted report showing:
    • Recent feedback trends (scores over time)
    • Top performing contexts (high scores)
    • Contexts needing review (low scores)
    • Recommendations for improvement
  6. Suggest which contexts to update or deprecate
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 19 lines · 9 tokens per session scan A 65c5d68ea2bd

Subscribe to this mod's changes

mcp-proxy-quality-report is a command published in the GitHub repository zach-source/mcp-rust-proxy (5 stars, last pushed 10mo ago), licensed MIT. It adds 9 tokens to every session and 143 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.