Introduction

lurq is a continuously-updated, evidence-scored index of JS/TS frameworks and libraries, exposed to AI coding assistants as an MCP server, a CLI, and an installable agent skill. It gives your agent fresh, objective dependency recommendations, including packages published after the model's training cutoff.

Think of lurq as a companion to your coding agent: lurq recommends and explains packages; your agent writes the code. It's tuned for token cost, speed, and retrieval quality.

Why it exists

Coding agents are good at writing code but bad at picking dependencies. They:

• recommend packages frozen at their training cutoff, missing anything newer;
• hallucinate package names that were never published;
• lean on whatever was popular when the model was trained, not what's healthy now.

…and they write code against APIs that moved. A package name can be right, healthy, and current, and the call your agent just wrote still wrong, because the symbol it used was removed three majors ago.

lurq fixes this with a live index built from public signals (npm, GitHub, deps.dev, OSV, bundlephobia), plus two things metadata can't tell you: what a version actually exports, extracted from its shipped code, and whether a set of packages actually installs together, established by running it. Scores are computed, never hand-written, and every response carries a dataAsOf timestamp.

What you get

Once connected, your agent can call eleven MCP tools:

Choosing

• recommend: best current packages for a need
• evaluate: full evidence read for one package
• compare: rank 2–5 packages by health
• verify: is a package real, healthy, and safe?

Whole stacks

• compat: will these packages actually install together?
• plan: source every slot in a stack at once
• diagram: a reference-architecture diagram for a stack

Writing the code

• usage: a version's real API, and what changed since the one you know
• resolve_surface: exactly what a version exports at runtime
• diff_surface: what a version bump adds, removes, or re-shapes
• report_outcome: tell lurq how the pick worked out

The same engine is available from your terminal — see the CLI reference — including lurq check-upgrade, which tells you whether an upgrade removes a symbol your code references, with no test suite required.

Scope

Ready to connect your agent? Head to the Quick start.