Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
Devstack is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
Dev-registry data: npm/PyPI/Docker/VS Code packages, dep graphs, vulns, 50+ ecosystems.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http devstack-mcp https://devstack-mcp.vercel.app/mcp
# 2 — ask your agent for something these tools do
# get_package, search_packages, get_versions and 7 more
Devstack costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ISAll 13 servers
IsaiahDupree13 servers
8 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http devstack-mcp https://devstack-mcp.vercel.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Full 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 pac
| Parameter | Type | Required | Notes |
|---|---|---|---|
| registry | string | yes | Target registry. "all" fans out to every registry and merges results. |
| name | string | yes | Package name / id. Supports scoped npm ids (@scope/pkg), Docker namespaces (ns/name or a bare name for official images), and VS Code publisher.extension ids. |
Search 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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| registry | string | yes | Target registry. "all" fans out to npm, Docker, and VS Code and merges results. pypi returns not_supported. |
| q | string | yes | Search query. |
| limit | integer | no | Max results per registry. Clamped to 1-50. Default 20. |
List 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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| registry | string | yes | Target registry. "all" is not supported here — pick one. |
| name | string | yes | Package name / id (scoped npm ids, Docker namespaces, and VS Code publisher.extension ids supported). |
Download 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| registry | string | yes | Target registry. Only npm and pypi expose download stats. |
| name | string | yes | Package name. |
The 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 ca
| Parameter | Type | Required | Notes |
|---|---|---|---|
| system | string | yes | Package system / ecosystem for deps.dev. Case-insensitive, lowercased server-side. |
| name | string | yes | Package name / id. |
| version | string | yes | Exact version to resolve (e.g. 18.2.0). Required. |
Known 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 cl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ecosystem | string | yes | OSV ecosystem, CASE-SENSITIVE (e.g. npm, PyPI, Go, crates.io, Maven, NuGet, RubyGems). |
| name | string | yes | Package name. |
| version | string | no | Exact version to filter advisories to. Omit for full history. |
Scan 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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| queries | array | yes | Up to 100 { ecosystem, name, version? } queries, ideal for a whole lockfile. |
Health 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 mir
| Parameter | Type | Required | Notes |
|---|---|---|---|
| system | string | yes | Package system / ecosystem for deps.dev. Case-insensitive, lowercased server-side. |
| name | string | yes | Package name / id. |
| version | string | no | Exact version. Omit for the (moving) registry default version. |
Look 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 vulnerabil
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Exact package name to look up across registries. |
| ecosystem | string | no | Narrow to one ecosystem (e.g. pypi, npm, cargo). Omit to search all. |
| limit | integer | no | Max results. Clamped to 1-50. Default 20. |
Full 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ecosystem | string | yes | Target ecosyste.ms ecosystem slug (e.g. npm, pypi, cargo, rubygems). |
| name | string | yes | Package name / id. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Devstack or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.0.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest3e8c4ee598a99a6cf60b249424218bbd987f842d4b3959059c358049abacebfd
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_package | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_packages | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_versions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_downloads | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| get_dependency_graph | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_vulnerabilities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| scan_vulnerabilities_batch | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_insights | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_ecosystems | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_ecosystems_package | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest3e8c4ee598a99a6c
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Devstack can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.