Skip to content

DepScout

by yc-droid · remote · no sign-in to list tools · v1.0.0 · published by GitHub user yc-droid

Scan packages and lockfiles (npm, PyPI, Go, Maven, Cargo, NuGet) for vulnerabilities and malware.

Changes · 3
CompareRegistry entry

4 tools: 3 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http depscout https://depscout.salesup.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 3Claude Code: ask
  • check_dependenciesCheck up to 50 packages at exact versions (for example from package.json, package-lock.json, requirements.txt, go.mod, pom.xml, Cargo.toml or a .csproj) against OSV.dev in one batc…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check up to 50 packages at exact versions (for example from package.json, package-lock.json, requirements.txt, go.mod, pom.xml, Cargo.toml or a .csproj) against OSV.dev in one batch. Returns a summary count and only the packages with problems: malicious-package flags first, then vulnerabilities by severity with the version that fixes each and the minimum upgrade target. Use when the user pastes a dependency file or list, or asks to "audit my dependencies" or "check my package.json / requirements.txt", or which dependencies are vulnerable or outdated. Entries without an exact version are skipped and listed; transitive dependencies are only checked if included in the list.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
    • title: Check a dependency list
  • check_lockfileAudit a whole lockfile or dependency file in one call, including transitive dependencies where the file records them.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Audit a whole lockfile or dependency file in one call, including transitive dependencies where the file records them. Paste the file content as-is: package-lock.json, npm-shrinkwrap.json, yarn.lock, pnpm-lock.yaml, requirements.txt (== pins), poetry.lock, uv.lock, Pipfile.lock, Cargo.lock, go.sum, go.mod, packages.lock.json (NuGet) or gradle.lockfile. Up to 3,000 packages are checked against OSV.dev. Returns a summary and only the packages with problems: malicious-package flags first, then vulnerabilities by severity with the minimum upgrade target. Use when the user pastes or attaches a lockfile, asks for a full or transitive dependency audit, or asks "is my project vulnerable?". Prefer this over check_dependencies when the user has the file itself.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
    • title: Audit a lockfile
  • check_packageCheck one open-source package (npm, PyPI, Go, Maven, crates.io or NuGet) for safety and freshness.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check one open-source package (npm, PyPI, Go, Maven, crates.io or NuGet) for safety and freshness. Returns a malicious-package flag (from OSV MAL- and malware advisories), known vulnerabilities with severity and the version that fixes each, the minimum version that clears all of them, the latest stable version, whether the given version is outdated or deprecated, licences, last release date, and the linked repository's OpenSSF Scorecard. If no version is given, the latest version is checked. Use when the user asks "is <package> safe?", "is it malware?", "which version should I use?", "should I upgrade?", or about a package's known CVEs, and before recommending any package or version to install (npm install, pip install, go get, cargo add, etc.). Data comes from OSV.dev and deps.dev; newly published malware may not be listed yet.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
    • title: Check a package
Only reads 1Claude Code: allow
  • get_vulnerabilityLook up one vulnerability or malicious-package advisory by ID (CVE, GHSA, PYSEC, GO, RUSTSEC, MAL and other OSV IDs) and return its summary, severity, CVSS vector, aliases, publish…Reads text others writeNo findings

    Why it is in this group

    • The name "get_vulnerability" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Look up one vulnerability or malicious-package advisory by ID (CVE, GHSA, PYSEC, GO, RUSTSEC, MAL and other OSV IDs) and return its summary, severity, CVSS vector, aliases, publish date, the affected packages with their affected and fixed version ranges, and key references. Use when the user mentions a specific advisory or CVE ID ("what is CVE-2021-44228?", "am I affected by this GHSA?") and wants to know what it is, what is affected or which version fixes it. Only covers advisories in OSV.dev.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
    • title: Get vulnerability details

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http depscout https://depscout.salesup.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__depscout__get_vulnerability"
    ],
    "ask": [
      "mcp__depscout__check_package",
      "mcp__depscout__check_dependencies",
      "mcp__depscout__check_lockfile"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as depscout. Review it before you use it.

Capability tags behind 4 rules
  • mcp__depscout__check_package untrusted-input
  • mcp__depscout__check_dependencies untrusted-input
  • mcp__depscout__check_lockfile untrusted-input
  • mcp__depscout__get_vulnerability untrusted-input