dep-scout

io.github.unievolver由 GitHub 帳號 unievolver 發布v0.2.0更新於 Oct 25, 2026

Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them.

已驗證STDIO僅桌面開發者工具安全與監控

概覽

AI 產生的概覽

一個本機 MCP 伺服器,讓程式設計助理在六個套件倉庫中尋找成熟套件、評估重用品質,並檢查安全與授權風險。

可以做什麼
在 crates.io、npm、PyPI、Go、Maven Central 與 NuGet 中依功能描述搜尋套件,回傳附有 0–100 重用評分與警告的排序候選。依確切名稱與生態深入檢視單一套件的授權、已知 OSV 漏洞、棄用或撤回狀態、版本需求、熱門程度與最近更新時間。搜尋官方 MCP 登錄檔,找出既有的 MCP 伺服器,避免重複開發。
適用情境
適合在 AI 程式設計助理準備從零實作某項功能時,先確認是否已有維護良好的套件可用;也適合在採用某個相依套件前,快速了解其健康度、授權與已知漏洞。
執行需求
以本機 stdio 程序執行,可透過 .mcpb 套件散布,或以較新的 Rust 工具鏈(edition 2024)從原始碼建置。不需要 API 金鑰或環境變數,所有資料來源都是公開的免金鑰 API,但需要網路存取。
安裝前請注意
僅進行唯讀查詢,但查詢內容與套件名稱會傳送給第三方公開服務(crates.io、npm、PyPI、deps.dev、Maven Central、NuGet、OSV、MCP 登錄檔)。評分以及授權、漏洞標記僅為參考性啟發式結果,不能取代自行審查。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 dep-scout,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

dep-scout

先查再造 (research before you build) — an MCP server that stops AI coding agents from reinventing the wheel.

Before an agent writes a feature from scratch, dep-scout searches the right registry — crates.io (Rust), npm (JS/TS/frontend), PyPI (Python), pkg.go.dev (Go), Maven Central (Java/Kotlin) or NuGet (.NET) — for a mature package that already solves the problem, and scores each candidate on reuse quality (popularity, maintenance recency, version stability, metadata) — and flags known security advisories (OSV) and license-compliance risks. The agent then reuses a proven, safe solution instead of hand-rolling buggy code. It can also search the official MCP registry so the agent reuses an existing MCP server instead of building one.

Works with Cursor (and any MCP client) over stdio. No API keys — every data source is a keyless public API.

Why

AI now writes a lot of code — and its worst habit is reimplementing solved problems, picking abandoned libraries, or hallucinating packages. dep-scout turns the best practice "don't build it if a maintained package already does it" into a tool the agent calls automatically, across languages.

Tools

ToolWhat it does
find_packagesGiven a feature description + ecosystem (rust | npm | python | go | maven | nuget), returns ranked candidates with a 0–100 reuse score, signals, and warnings.
inspect_packageDeep-dives one package by exact name + ecosystem: license (+ compliance flag), known OSV vulnerabilities, deprecation/yank status, runtime/version requirements, downloads or GitHub stars, last-update recency.
find_mcp_serversSearches the official MCP registry for existing MCP servers (name, install info, repo, status) — so you don't rebuild one.

ecosystem accepts aliases: js/ts/javascript/typescript/node/frontend → npm, py/pip → python, golang → go, java/kotlin/gradle/jvm → maven, dotnet/csharp/net → nuget, rs/cargo → rust.

Reuse score (0–100)

  • Popularity (≤40) — downloads normalised to a ~90-day window; for Go/Maven (no public download stats) GitHub stars are used as a proxy.
  • Maintenance (≤30) — how recently the package was updated.
  • Stability (≤15) — stable 1.0+ vs 0.x; penalty for pre-releases.
  • Metadata (≤15) — repository, docs/homepage, license present.
  • Security penalty — known OSV advisories on the resolved version sink the score and de-rank the candidate.
  • License flag — copyleft / commercially-restricted licenses (GPL, AGPL, LGPL, MPL, SSPL, BUSL…) are surfaced as compliance warnings.
  • Penalty — latest version yanked (crates/PyPI) or deprecated (npm).

Verdicts: ≥78 ✅ strongly recommend · 58–77 🟡 usable · 38–57 🟠 cautious · <38 🔴 find an alternative.

Ranking blends textual relevance (query-term overlap, exact-name match) with the reuse score and the registry's own ordering, so results are both on-topic and high quality.

Data sources (all keyless)

EcosystemSearchDetailsPopularity
Rustcrates.io API (relevance + downloads merge)crates.io APIcrates.io downloads (90-day)
npmregistry.npmjs.org/-/v1/searchregistry.npmjs.org/{pkg}/latestapi.npmjs.org (last-month)
Pythondeps.dev name search (+ token fallback)pypi.org/pypi/{pkg}/jsonpypistats (last-month)
Godeps.dev name searchdeps.dev v3 (GetPackage/GetVersion/GetProject)GitHub stars
Java/KotlinMaven Central solr searchdeps.dev v3GitHub stars
.NETNuGet search APINuGet search APINuGet total downloads
MCP serversofficial registry.modelcontextprotocol.io——
SecurityOSV.dev query (detail) + querybatch (flag) across all ecosystems

Python note: PyPI has no public full-text search API (the legacy XML-RPC search is gone and the web search is bot-blocked), so Python search is name-oriented via deps.dev. It excels when the query is/contains the library name; for pure capability phrases, prefer inspect_package with a known name.

Build

Requires a recent Rust toolchain (edition 2024).

bash
cargo build --release

The binary is produced at target/release/dep-scout (.exe on Windows).

Use in Cursor

  1. Register the MCP server. A portable project config lives at .cursor/mcp.json — it uses cargo run --release so no machine-specific paths are required. For global use, add an entry to ~/.cursor/mcp.json:

    json
    {  "mcpServers": {    "dep-scout": {      "command": "/absolute/path/to/dep-scout/target/release/dep-scout"    }  }}

    On Windows use ...\\target\\release\\dep-scout.exe. Build the release binary first (cargo build --release above) when using a direct binary path.

  2. Restart Cursor; you should see dep-scout with its tools enabled.

  3. The .cursor/rules/research-before-build.mdc rule makes the agent search before building. A portable, client-agnostic version lives at skill/SKILL.md.

How it talks

Standard MCP over stdio (JSON-RPC 2.0), built on the official rmcp SDK. Logs go to stderr so they never corrupt the protocol stream on stdout.

Roadmap

  • More ecosystems: Ruby (RubyGems), PHP (Packagist), Dart/Flutter (pub.dev).
  • Per-ecosystem popularity calibration (npm/PyPI volumes dwarf crates.io).
  • Last-update recency for NuGet; richer Maven search ranking.
  • Deeper repo health signals (open issues, release cadence, maintainer count).
  • A curated trust/quality dataset — the real moat over a plain registry mirror.

Project layout

src/  main.rs      # MCP server + tools (find_packages / inspect_package / find_mcp_servers)  model.rs     # Ecosystem enum, normalised Package, reuse scoring, relevance  sources.rs   # keyless registry clients (crates.io, npm, PyPI, deps.dev, MCP registry).cursor/  rules/research-before-build.mdc   # always-on Cursor rule  mcp.json                          # local server registrationskill/SKILL.md                      # portable skill for any MCP client

MCP Registry

Published to the official MCP Registry as io.github.unievolver/dep-scout. Download the .mcpb bundle from GitHub Releases or build from source with cargo build --release.

  • MCP Registry name: mcp-name: io.github.unievolver/dep-scout

License

MIT

來源:README.md,提交 0de4f9e

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.2.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分