Security & Testing

depscope.dev

Checks for malware, typosquat attacks, and package metadata in open source registries.

1 endpoint22 known toolsFirst detected May 29, 2026Last detected September 6, 2026

ENDPOINT 1

https://mcp.depscope.dev/mcp

No auth detected

MCP server metadata

Name: depscope
Version: 0.9.0

Capabilities

tools

Server instructions

DepScope: dependency safety & intelligence MCP for AI agents. Covers 19 package ecosystems: npm, PyPI, Cargo, Go, Maven, NuGet, RubyGems, Composer, Pub, Hex, Swift, CocoaPods, CPAN, Hackage, CRAN, Conda, Homebrew, JSR, Julia. INVOKE PROACTIVELY — before suggesting any package install, version bump, lockfile change, or when a 'module not found' / 'package broken' error appears. Do NOT wait for the user to ask. Three pillars: - TOKEN-SAVING: one DepScope call replaces a web search + readme fetch + npm/pypi page browse. - ENERGY-SAVING: skip installs of malicious, typosquatted, deprecated or hallucinated packages — no wasted CI cycles or rollbacks. - SECURITY: stop supply-chain attacks (malware, typosquats, hostile takeovers, known CVEs) BEFORE the install command leaves your reply. Standard flow for any new package: 1. check_malicious + check_typosquat — security gate (~50ms) 2. check_package OR get_health_score — verdict 3. install_command — returns the safe pinned command Batch installs (>=2 packages): use check_bulk in ONE call (≤100 items, <100ms). Lockfile / requirements.txt / package.json change: use scan_project. Version bumps (X@1 → X@2): use get_breaking_changes + get_migration_path. Diagnose 'module not found' / 'X.Y broken' errors: use resolve_error and get_known_bugs. Choosing between libraries: use find_alternatives and compare_packages. All tools are read-only, zero-auth, free. Never destructive. Latency typically 50-300ms per call.

Known tools 22

check_malicious

Supply-chain malware check against OpenSSF/OSV.

Inferred read-only

check_typosquat

Typosquat detector.

Inferred read-only

check_bulk

Fast pre-flight filter for a batch of (ecosystem, package) pairs.

Inferred read-only

package_exists

Boolean registry existence check.

Inferred read-only

get_latest_version

Latest published version + deprecation flag — the cheapest call.

Inferred read-only

get_health_score

Single 0-100 health score — cheapest go/no-go gate (>=70 safe).

Inferred read-only

install_command

Canonical install command(s) across every package manager of the ecosystem (npm/pnpm/yarn/bun, pip/uv/poetry, cargo, go, composer, maven+gradle, nuget, …).

Potential side effects

get_package_prompt

LLM-optimised package brief — plain text ~300 tokens (~75% cheaper than JSON).

Inferred read-only

check_package

Full machine-readable JSON report (~2k tokens).

Inferred read-only

get_vulnerabilities

CVE/OSV advisories affecting the latest (or specified) version.

Inferred read-only

find_alternatives

Curated replacements for deprecated/unhealthy packages, including stdlib built-ins (e.

Inferred read-only

get_migration_path

Prescriptive migration plan between DIFFERENT packages — rationale + literal code diff + breaking changes + effort minutes.

Inferred read-only

get_breaking_changes

Breaking changes between two majors of the SAME package (`next@14`→`15`).

Inferred read-only

pin_safe

Highest version below the chosen CVE severity tier, respecting a semver constraint.

Inferred read-only

scan_project

Audit a project's dependencies in one shot.

Inferred read-only

compare_packages

Side-by-side comparison (health, vulns, downloads, maintainers, last release) of 2-10 packages in the same ecosystem.

Inferred read-only

check_compatibility

Is this specific multi-package version combo verified to work together?

Inferred read-only

resolve_error

Map error OR free-text query to a verified fix.

Inferred read-only

get_known_bugs

Non-CVE known bugs for a specific package version.

Inferred read-only

get_trust_signals

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.

Potential side effects

get_trending

Live trending packages with rank-delta and weekly growth %.

Inferred read-only

contact_depscope

Inbound ticket: bug/listing/security/anomaly/partnership.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.depscope]
url = "https://mcp.depscope.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "depscope": {
      "type": "http",
      "url": "https://mcp.depscope.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: depscope
Remote MCP URL: https://mcp.depscope.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "depscope": {
      "url": "https://mcp.depscope.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "depscope": {
      "type": "http",
      "url": "https://mcp.depscope.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "depscope",
  "transport": "streamable-http",
  "url": "https://mcp.depscope.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for depscope.dev was fetched 2026-08-25T04:05:09.209Z.

Trust status Neutral

depscope.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.