1. Conduid
  2. Browser
  3. Qulib
MCP server · Browser

Qulib

by · github.com/TapeshN/qulib

Honest QA gap analysis for deployed web apps. Auth-aware scanning, real accessibility checks, and an MCP server for AI agents.

Unclaimed accessibilityai-agentsaxe-coremcpplaywrightqaquality-engineeringrelease-readinesstestingtypescript
InstallView source
34Low

Scored 27 days ago · breakdown

About Qulib

Qulib is an MCP server published by TapeshN in the Browser category: honest QA gap analysis for deployed web apps. Auth-aware scanning, real accessibility checks, and an MCP server for AI agents.

The repository has 2 stars and 0 forks, with the last commit 3 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/TapeshN/qulib

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Qulib

Powered by Claude · Grounded in docs

I know everything about Qulib. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.14.0v0.14.0 · 2 Jul 2026Security-hardening + entitlement release. Highlights: per-session rate limit on LLM-judge tools (QULIB_JUDGE_MAX_CALLS_PER_MIN); MCP errors no longer leak stack traces by default (QULIB_EXPOSE_ERROR_DETAIL opt-in); judge rubric moved to…
v0.13.0v0.13.0 · 27 Jun 2026Two features: the LLM-judge tools are now on the **CLI** (`qulib score-decisions` with a `--min-quality` CI gate, `qulib score-bug-report`), and **`qulib validate`** (+ MCP `qulib_validate_spec`) grades a deployed app against a supplied…
v0.12.0v0.12.0 · 27 Jun 2026The release-confidence verdict now gates CI.** `qulib confidence --fail-on <verdict>` exits non-zero when the verdict is at or worse than `caution`|`hold`|`block`; `--min-score <n>` gates on the 0–100 score. Prints `GATE: PASS|FAIL`;…
v0.11.0v0.11.0 · 27 Jun 2026Adds the two LLM-as-judge tools to npm: **qulib_score_bug_report** (grades a bug report vs a planted-bug target) and **qulib_score_decisions** (pivotal-decision evaluation — senior-correctness at agent decision forks). Both are…
v0.10.1v0.10.1 · 27 Jun 2026Patch release. Fixed Release confidence honesty notes:** present-but-excluded evidence sources (`not_applicable`, `unknown`, null score) are now narrated before uncollected model sources, so `maxListLength` truncation no longer drops notes…
Questions

About Qulib

How do I install Qulib?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Qulib safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Qulib still maintained?

Yes — the latest release is v0.14.0 (2 Jul 2026), and the last commit was 3 months ago. The repository has 2 stars.