mcp server

DepScope

Package intelligence MCP for AI agents — 22 tools, 19 ecosystems, AGPL SDK, free.

Description as published by the maintainer. Source

• version 0.9.24
• slowing

slowing — Most recent push to the repository was 2026-05-05.

What this server can do

22 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

check_bulk(items)

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}. Required: items.

check_compatibility(packages)

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}. Required: packages.

check_malicious(package, ecosystem)

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}. Required: ecosystem, package.

check_package(package, version, ecosystem)

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}. Required: ecosystem, package.

check_typosquat(package, ecosystem)

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}. Required: ecosystem, package.

compare_packages(packages, ecosystem)

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. Required: ecosystem, packages.

contact_depscope(body, kind, name, email, company, package, subject, version, expected, observed, ecosystem, tool_called, evidence_url)

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}.

find_alternatives(package, ecosystem)

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}}. Required: ecosystem, package.

get_breaking_changes(package, ecosystem, to_version, from_version)

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}}. Required: ecosystem, package.

get_health_score(package, ecosystem)

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}. Required: ecosystem, package.

get_known_bugs(package, version, ecosystem)

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}}. Required: ecosystem, package.

get_latest_version(package, ecosystem)

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}. Required: ecosystem, package.

get_migration_path(ecosystem, to_package, from_package)

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}. Required: ecosystem, from_package, to_package.

get_package_prompt(package, ecosystem)

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. Required: ecosystem, package.

get_trending(limit, scope, ecosystem)

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}}.

get_trust_signals(package, ecosystem)

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. Required: ecosystem, package.

get_vulnerabilities(package, ecosystem)

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}}. Required: ecosystem, package.

install_command(package, version, ecosystem)

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[]}. Required: ecosystem, package.

package_exists(package, ecosystem)

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}. Required: ecosystem, package.

pin_safe(package, ecosystem, constraint, min_severity, include_prerelease)

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[]}. Required: ecosystem, package.

resolve_error(error, limit, query, context)

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}].

scan_project(packages, ecosystem)

Audit a project's dependencies in one shot. Returns a single-sentence `verdict` (e.g. "DO NOT INSTALL — 1 hallucinated: fastapi-turbo") that an agent can paste into its reply, plus per-package health/vulns/recommendation. Detects hallucinated packages, deprecated, typosquats, critical vulnerabilities. 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/Cargo.toml; agent generated install command; 'is my stack OK'. RETURNS: JSON with `verdict`, `project_risk`, `summary.hallucinated_packages`, `summary.deprecated_packages`, per-package health. Required: packages.

Last successful function declaration observed on 2026-08-13. Source: https://mcp.depscope.dev/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://mcp.depscope.dev/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/cuttalo/depscope-mcp
• Website — https://depscope.dev
• npm: depscope-mcp
• Remote endpoint (streamable-http) — https://mcp.depscope.dev/mcp

Related, by what their authors tagged them

• io.github.alisaitteke/npm-mcp — last commit 2026-01-29, shares npm, package-manager
  MCP server for npm package management, security analysis, and compatibility checking
• io.github.getmcpm/cli — last commit 2026-08-08, shares package-manager, security
  MCP package manager with trust scoring. Search, install, and audit MCP servers.
• Draugr — last commit 2026-08-06, shares security, supply-chain-security, vulnerability-scanner
  Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
• io.github.eltociear/skill-audit-mcp — last commit 2026-08-02, shares security, supply-chain-security, vulnerability-scanner
  Scan agent skills and MCP servers for malicious patterns before you load them
• io.github.DigiCatalyst-Systems/dep-diff-mcp — last commit 2026-04-25, shares npm, pypi, security
  Translates a lockfile diff into a human-readable upgrade plan for npm and PyPI.
• com.datakoot/package-intel-mcp — last commit 2026-08-02, shares npm, pypi
  npm, PyPI & crates.io intel for AI agents: versions, popularity, deps, health. No API keys.
• Open Source Intelligence MCP — last commit 2026-07-16, shares npm, pypi
  GitHub project health, package dependency risk, trending repos, license & package comparison.
• pkgxray — last commit 2026-08-06, shares npm, supply-chain-security
  Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
• io.github.amitsingh-24/pixlint — last commit 2026-07-27, shares pypi
  Lint, curate & prepare computer-vision datasets from your AI assistant — MCP server, 67 tools
• io.github.davidmosiah/agent-seo-engine — last commit 2026-07-03, shares pypi
  Agent-first local SEO quality, intent and opportunity engine with CLI and optional MCP server.

These share tags the maintainers applied themselves, such as npm, package-manager, security, supply-chain-security. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, cargo, chatgpt, claude, cursor, llm, mcp, mcp-server, model-context-protocol, npm, package-manager, pypi, security, slopsquatting, supply-chain-security, vulnerability-scanner, windsurf.