DepScope
DepScope
AIエージェントのためのパッケージインテリジェンス。 AIコーディングエージェント(Claude、ChatGPT、Cursor、Windsurf、Copilot、Cline)が、19のエコシステム全体でハルシネーション(幻覚)、非推奨、または悪意のあるパッケージをインストールするのを防ぎます。
→ depscope.dev で公開中 · 840万以上のパッケージ · 4万2000以上の脆弱性(99%がEPSS強化済み) · 認証不要 · 無料
クイックスタート (MCP)
Claude Desktop / Cursor / Windsurf — リモート
{
"mcpServers": {
"depscope": {
"url": "https://mcp.depscope.dev/mcp"
}
}
}Claude Code / ローカル — stdio
{
"mcpServers": {
"depscope": {
"command": "npx",
"args": ["-y", "depscope-mcp"]
}
}
}MCPサーバーのソースコードは cuttalo/depscope-mcp (AGPL-3.0) にあります。
Related MCP server: mcp-dep-tools
機能
19のパッケージエコシステムに対応した22のMCPツール:
npm · pypi · cargo · go · composer · maven · nuget · rubygems · pub · hex · swift · cocoapods · cpan · hackage · cran · conda · homebrew · jsr · julia
ツール | 目的 |
| 完全な安全性チェック:非推奨・脆弱性・健全性・推奨事項 |
| 悪意のあるパッケージの検出 |
| 一般的な名称に対するタイポスクワッティング検出 |
| ハルシネーション検出 (404 = LLMによる捏造) |
| 内訳付きの0〜100の健全性スコア |
| 脆弱性情報 + 深刻度スコア |
| 非推奨/放棄されたパッケージの代替案提案 |
| メジャーバージョン移行時の注意点 |
| パッケージの既知の問題 |
| 並列比較 |
| スタックレベルの互換性チェック |
| エラーメッセージ → 原因と修正案 |
| 対象エコシステム向けの検証済みインストールコマンド |
| 最新の安定版バージョン + 成熟度シグナル |
| 推奨される安全なバージョン指定 |
| マルチシグナル信頼スコア |
| ステップバイステップのアップグレード計画 |
| 依存関係マニフェストの一括スキャン |
| バッチ処理用の高速事前フィルタリング |
| エコシステム別のトレンドパッケージ |
| LLMフレンドリーなコンパクトな要約 |
| 不足パッケージや誤検知の報告 |
REST API
同じデータをプレーンなHTTPSで提供 — MCPクライアントは不要です。
curl https://depscope.dev/api/check/npm/lodash
curl https://depscope.dev/api/check/pypi/requests
curl https://depscope.dev/api/check/cargo/serde完全なリファレンス: depscope.dev/integrate
なぜ必要なのか
LLMは、実在するように見えて実際には存在しないパッケージ名(fastapi-turbo、lodahs、tokio-stream-extrasなど)を頻繁に捏造します。エージェントがこれらをインストールしようとすると、攻撃者のタイポスクワッティングに遭遇する可能性があります。DepScopeは、インストール前にすべてのパッケージを検証します。
詳細: depscope.dev/why
料金
無料。 認証不要。寛大なレート制限。
より高いクォータ、SLA、またはオンプレミスでの導入が必要な場合は、depscope@cuttalo.com までお問い合わせください。
オープンソースとプロプライエタリ
このリポジトリはドキュメントのみを含むランディングページです。
MCPサーバー (クライアントSDK) — オープンソース、AGPL-3.0: → cuttalo/depscope-mcp → npm: depscope-mcp
バックエンド (API + インテリジェンス層) — プロプライエタリ、
depscope.devでホスト。
この分離により、クライアントを無料かつ監査可能でコミュニティが拡張可能な状態に保ちつつ、それを支えるインフラストラクチャを維持しています。
リンク
ホームページ · depscope.dev
APIドキュメント · depscope.dev/integrate
MCPサーバーソース · cuttalo/depscope-mcp
npm · depscope-mcp
Glamaリスト · glama.ai/mcp/servers/cuttalo/depscope
Awesome MCP · punkpeye/awesome-mcp-servers
ライセンス
このREADMEおよび付属のランディングファイル: CC-BY-4.0。 MCPクライアントSDK: AGPL-3.0 (cuttalo/depscope-mcp を参照)。 バックエンドサービス: プロプライエタリ。
Built by Cuttalo srl · イタリア 🇮🇹
Available Tools
22 toolscheck_bulkARead-onlyIdempotentInspect
Fast pre-flight filter for a batch of (ecosystem, package) pairs. DB-only, <100ms for 100 items. USE WHEN: about to emit npm install a b c … or pip install a b c … — catches hallucinated names, stdlib, typos, and known-bad in ONE call. NOT a dep-tree audit (use scan_project for that). RETURNS: per-item {status: exists|stdlib|malicious|typosquat_suspect|historical_incident|unknown}.
Inputs: items (required).
check_compatibilityARead-onlyIdempotentInspect
Is this specific multi-package version combo verified to work together? USE WHEN: pinning a stack (next@15 + react@19 + node@22); before recommending a version matrix. RETURNS: {compatible, conflicts[], notes}.
Inputs: packages (required).
check_maliciousARead-onlyIdempotentInspect
Supply-chain malware check against OpenSSF/OSV. USE WHEN: about to suggest install of an unvetted/unfamiliar package; name came from a blog/tutorial. Call BEFORE check_package for untrusted pkgs. RETURNS: {is_malicious, threat_tier, source}.
Inputs: ecosystem (required), package (required).
check_packageARead-onlyIdempotentInspect
Full machine-readable JSON report (~2k tokens). USE WHEN: you need to programmatically parse specific fields (CI gating, UI, sub-field extraction). Otherwise prefer get_package_prompt. RETURNS: {package, health:{score}, vulnerabilities[], latest, deprecated, maintainers, recommendation}.
Inputs: ecosystem (required), package (required), version.
check_typosquatARead-onlyIdempotentInspect
Typosquat detector. USE WHEN: name differs from a well-known package by 1-2 chars (lodsh, reqeusts); copy-paste from unreliable source; downloads near zero but name looks familiar. RETURNS: {is_typosquat, likely_target, confidence}.
Inputs: ecosystem (required), package (required).
compare_packagesARead-onlyIdempotentInspect
Side-by-side comparison (health, vulns, downloads, maintainers, last release) of 2-10 packages in the same ecosystem. USE WHEN: 'X vs Y' / 'should I pick X or Y'. RETURNS: table-shaped JSON, one row per package.
Inputs: ecosystem (required), packages (required).
contact_depscopeAInspect
Inbound ticket: bug/listing/security/anomaly/partnership. USE WHEN: reporting wrong data (bug), requesting a new pkg/ecosystem index (listing), disclosing a DepScope security issue (security), flagging a concrete mismatch in another tool's output vs. authoritative source (anomaly — provide tool_called+observed+expected), or partnership/press (partnership). RETURNS: {ticket_id} or {anomaly_id}.
Inputs: kind, email, subject, body, +9 more.
find_alternativesARead-onlyIdempotentInspect
Curated replacements for deprecated/unhealthy packages, including stdlib built-ins (e.g. fs.rm for rimraf). USE WHEN: pkg flagged AVOID/URGENT; 'what to use instead of X'; before guessing a replacement name. RETURNS: {alternatives[]: {name, reason, is_stdlib}}.
Inputs: ecosystem (required), package (required).
get_breaking_changesARead-onlyIdempotentInspect
Breaking changes between two majors of the SAME package (next@14→15). USE WHEN: user is bumping a major; before recommending a major upgrade. Different from get_migration_path (same pkg vs. different pkg). RETURNS: {breaking_changes[]: {area, description, hint}}.
Inputs: ecosystem (required), package (required), from_version, to_version.
get_health_scoreARead-onlyIdempotentInspect
Single 0-100 health score — cheapest go/no-go gate (>=70 safe). USE WHEN: CI gating or pkg already screened for malware/typos. NOT a first screen — run check_malicious + check_typosquat first. For a verbal verdict use get_package_prompt. RETURNS: {score, verdict}.
Inputs: ecosystem (required), package (required).
get_known_bugsARead-onlyIdempotentInspect
Non-CVE known bugs for a specific package version. USE WHEN: unexpected behavior that is NOT a security issue; a pinned version misbehaves. RETURNS: {bugs[]: {title, fixed_in, workaround}}.
Inputs: ecosystem (required), package (required), version.
get_latest_versionARead-onlyIdempotentInspect
Latest published version + deprecation flag — the cheapest call. USE WHEN: only a version string matters (pinning a dep, answering 'what version of X'). If you also need health/vulns use check_package. RETURNS: {latest, deprecated, published_at}.
Inputs: ecosystem (required), package (required).
get_migration_pathARead-onlyIdempotentInspect
Prescriptive migration plan between DIFFERENT packages — rationale + literal code diff + breaking changes + effort minutes. USE WHEN: replacing request→axios, moment→dayjs, flask→fastapi, etc.; both endpoints known. RETURNS: {rationale, diff, breaking_changes[], estimated_minutes}.
Inputs: ecosystem (required), from_package (required), to_package (required).
get_package_promptARead-onlyIdempotentInspect
LLM-optimised package brief — plain text ~300 tokens (~75% cheaper than JSON). Verdict (SAFE/AVOID/URGENT/MALICIOUS) + health + vulns + alternatives + maintainer alerts. USE WHEN: you want to reason over a package and drop the output directly in context; 'is X safe'. PREFER THIS over check_package in 95% of LLM cases. RETURNS: plain-text brief.
Inputs: ecosystem (required), package (required).
get_trendingARead-onlyIdempotentInspect
Live trending packages with rank-delta and weekly growth %. USE WHEN: 'what is rising in npm/PyPI/Cargo right now'; recommendation not biased by training-data cutoff. RETURNS: {items[]: {name, rank, rank_delta, weekly_growth_pct}}.
Inputs: ecosystem, scope, limit.
get_trust_signalsARead-onlyIdempotentInspect
One-call aggregate of ALL non-CVE supply-chain trust signals: maintainer trust (bus factor, ownership changes), OpenSSF Scorecard, quality (criticality, release velocity, publish security), and SLSA/Sigstore provenance. USE WHEN: deep-vetting a package beyond CVEs (hardened/regulated env, SBOM/compliance, small-pkg ownership review, choosing between healthy candidates). Runs 4 backend endpoints in parallel. RETURNS: {maintainer, scorecard, quality, provenance} — each may be null if its backend call failed.
Inputs: ecosystem (required), package (required).
get_vulnerabilitiesARead-onlyIdempotentInspect
CVE/OSV advisories affecting the latest (or specified) version. USE WHEN: security-sensitive project; user asks 'any CVEs in X'; you already know the pkg exists. RETURNS: {vulnerability_count, vulnerabilities[]: {id, severity, cvss, fixed_in}}.
Inputs: ecosystem (required), package (required).
install_commandARead-onlyIdempotentInspect
Canonical install command(s) across every package manager of the ecosystem (npm/pnpm/yarn/bun, pip/uv/poetry, cargo, go, composer, maven+gradle, nuget, …). USE WHEN: emitting an install line and you want correct flags. RETURNS: {primary, variants[]}.
Inputs: ecosystem (required), package (required), version.
package_existsARead-onlyIdempotentInspect
Boolean registry existence check. USE WHEN: about to emit a package name in an install command but unsure it exists; verifying a name generated from training data. RETURNS: {exists}.
Inputs: ecosystem (required), package (required).
pin_safeARead-onlyIdempotentInspect
Highest version below the chosen CVE severity tier, respecting a semver constraint. USE WHEN: writing a package.json/requirements.txt line; resolving dependabot by lowest-risk patched version. RETURNS: {recommended_version, walk_log[]}.
Inputs: ecosystem (required), package (required), min_severity, constraint, +1 more.
resolve_errorARead-onlyIdempotentInspect
Map error OR free-text query to a verified fix. USE WHEN: user pastes a concrete error/stack (ENOENT, ImportError, build failure) — pass error. OR user describes a symptom ('webpack slow', 'pip stuck') — pass query. Always prefer this over guessing a fix. RETURNS: exact-match {status, solution, confidence, source_url} or search results [{title, summary, source_url}].
Inputs: error, query, context, limit.
scan_projectARead-onlyIdempotentInspect
Full dep-list audit with per-package health+vulns and prioritized actions (REMOVE NOW / URGENT / REPLACE / REVIEW). Accepts EITHER {ecosystem, packages:[name@ver, …]} (up to 100, returns JSON) OR {packages:[{ecosystem, package}, …]} (up to 50, mixed ecosystems, returns text brief). USE WHEN: user pastes package.json/requirements.txt; 'is my stack OK'. Unlike check_bulk this fetches full health/vulns. RETURNS: JSON or text per shape.
Inputs: packages (required), ecosystem.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Each tool has a clearly distinct purpose: checks for typosquatting, malware, compatibility, health, vulnerabilities, etc. Even similar tools like `check_package` and `get_package_prompt` are differentiated by output format (JSON vs text) and use case.
Most tools follow a verb_noun pattern (e.g., `check_malicious`, `get_latest_version`), but a few like `package_exists` (noun_verb) and `install_command` (verb_noun but combined) deviate slightly. The pattern is mostly consistent with lowercase underscores.
With 22 tools, the server covers a wide range of dependency analysis needs. While slightly above the typical 3-15 range, each tool serves a specific, non-redundant purpose, making the count appropriate for its comprehensive scope.
The tool set covers nearly the entire lifecycle of package evaluation: existence, health, security, compat, migration, alternatives, trending, error resolution, and project audit. No obvious gaps for the intended domain.
Maintenance
Related MCP Connectors
Free MCP security tools for AI coding agents. Check npm/PyPI package versions, identify known OSV vulnerabilities, compare with the latest releases, and review up to 3 dependencies before deployment.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Protects AI coding agents from installing malicious open source packages. Every npm and PyPI package is checked against SafeDep’s real-time threat intelligence before installation.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP security server for AI coding agents. 12 tools: pre-install guardian, vulnerability audit, supply-chain attack detection via static code analysis, and CycloneDX 1.6 SBOM generation. Zero runtime dependencies.15120 npm15Apache 2.0
- AlicenseAqualityDmaintenanceMCP server providing dependency and package management tools for AI agents. Analyze licenses, find outdated packages, visualize dependency trees, estimate bundle sizes, and audit security vulnerabilities.542 npmMIT
- AlicenseNot gradedqualityCmaintenanceVet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.102 npm13Business Source 1.1
- AlicenseNot gradedqualityDmaintenanceValidates and checks packages across 19 ecosystems to prevent AI agents from installing hallucinated, deprecated, or malicious packages.60 npmAGPL 3.0