devstack-mcp

Dev-registry data: npm/PyPI/Docker/VS Code packages, dep graphs, vulns, 50+ ecosystems.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Dev-registry data: npm/PyPI/Docker/VS Code packages, dep graphs, vulns, 50+ ecosystems.

    How to connect

    How to connect devstack-mcp to Claude

    The server address to paste into Claude settings:

    https://devstack-mcp.vercel.app/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect devstack-mcp to ChatGPT

    The server address to paste into ChatGPT settings:

    https://devstack-mcp.vercel.app/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect devstack-mcp to Cursor

    The server address to paste into Cursor settings:

    https://devstack-mcp.vercel.app/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (10)

    Raw names from tools/list. Only developers need these.

    get_packageFull normalized details for one package by registry + name, in a single unified Package shape across npm, PyPI, Docker Hub, and the VS Code Marketplace. name handles scoped npm ids (e.g. @types/node), Docker namespaces (e.g. library/nginx or a bare nginx for official images), and VS Code publisher.extension ids. With registry=all the request fans out to every registry in parallel and returns a packages array (missing registries are silently dropped); otherwise a single package is returned.
    search_packagesSearch a registry for packages matching q. registry=all fans out to npm, Docker Hub, and the VS Code Marketplace and merges the results. PyPI has no public search API, so registry=pypi returns 400 not_supported — look a PyPI package up by name via get_package instead. Results are normalized PackageSummary items (npm adds a relevance score; Docker adds isOfficial).
    get_versionsList published versions (npm/PyPI), image tags (Docker Hub, most recent 25), or extension versions (VS Code) for a package. registry=all is NOT supported here — pick a single registry. Each item carries version and released, plus registry-specific extras (files for PyPI, size for Docker tags).
    get_downloadsDownload statistics for a package. Only npm (via api.npmjs.org) and PyPI (via pypistats.org) support this; any other registry returns 400 not_supported. npm returns a period window with downloads, start, and end; PyPI returns last_day, last_week, and last_month totals.
    get_dependency_graphThe fully resolved dependency graph for one exact package version, via deps.dev. Returns a flat nodes[] array plus integer-index edges[] (walk from/to to rebuild the tree). Each node carries relation (self | direct | indirect) and a direct boolean; node[0] is always the queried root (relation: self). Node order is NOT stable — look nodes up by name/relation, never by positional index. system is case-insensitive and lowercased (npm, pypi, cargo, go, maven, nuget). version is REQUIRED (a graph is resolved for one exact version).
    get_vulnerabilitiesKnown vulnerabilities (CVE / GHSA / PYSEC / GO advisories) for a package, via OSV.dev. Pass version to filter to advisories affecting that exact version, or omit it for the package's full advisory history. Each result carries the OSV id, cross-id aliases, a severity word grade (LOW|MODERATE|HIGH|CRITICAL), the cvss vector string, affectedRanges with fixed-version events, references, and cwes. A clean package returns count: 0 with an empty list (not an error). ecosystem is CASE-SENSITIVE — use OSV's spelling (npm, PyPI, Go, crates.io, Maven, NuGet, RubyGems, …). Use scan_vulnerabilities_batch for lockfile batch scans.
    scan_vulnerabilities_batchScan many packages in one call — ideal for a whole lockfile. Pass a queries[] array (max 100) of { ecosystem, name, version? }; results are returned positionally aligned, one row per query, each with a count and a hydrated vulns[] array. Advisories are de-duplicated and hydrated across the batch. ecosystem is CASE-SENSITIVE (OSV spelling).
    get_insightsHealth and security insights for a package's source project, via deps.dev. Returns the linked source repository, GitHub stars/forks/openIssues, licenses, resolved dependencyCount, security advisories, and the full OSSF Scorecard (ossfScore 0..10 plus the per-check breakdown). Omit version to use the registry default version — note deps.dev's default is a MOVING target and an unverified default mirror may have no computed scorecard (ossfScore: null); pin version for a stable, scorecard-backed result. system is lowercased (npm, pypi, cargo, go, maven, …).
    search_ecosystemsLook a package name up across 50+ registries at once, via ecosyste.ms. This is an EXACT-name lookup (not fuzzy full-text): q=react returns the react package everywhere it exists (npm, cargo, nuget, pub, bower, …), each as a normalized ecosystemsPackage with reverse-dependency counts. Pass ecosystem to narrow to one registry. Results carry dependentReposCount, dependentPackagesCount, and vulnerabilityCount.
    get_ecosystems_packageFull normalized metadata for one package on one of 50+ registries, via ecosyste.ms — including the fields v1 registries can't give you: dependentReposCount and dependentPackagesCount (reverse dependencies), ecosystem, and vulnerabilityCount. Scoped/namespaced names are handled automatically. Returns 404 if the package does not exist on that ecosystem.