Local MCP capabilities provider for Expo
Socket.dev 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.
What it does
Hosted supply-chain security MCP server that scores npm/PyPI/Maven/Go packages for vulnerabilities, maintenance health and behavioral risk.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http socket-dev-mcp https://mcp.socket.dev/
# 2 — ask your agent for something these tools do
# depscore, organizations, alerts and 4 more
Socket.dev costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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, read from the address; if the publisher says otherwise, swap that one word.
claude mcp add --scope user --transport http socket-dev-mcp https://mcp.socket.dev/Reconnect, or start a new session, and the tools appear in the model’s tool list.
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.
7 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.
Get the dependency score of packages with the depscore tool from Socket. Use 'unknown' for version if not known. Use this tool to scan dependencies for their quality and security on existing code or when code is generated. Stop generating code and ask the user how to proceed when any of the scores are low. When checking dependencies, make sure to also check the imports in the code, not just the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| packages | array | yes | Array of packages to check |
| platform | string | no | Optional OS-architecture hint (e.g., 'linux-x64', 'darwin-arm64', 'win32-x64'). Used to select the most relevant artifact when a package has platform-specific builds. |
List the Socket organizations the authenticated user belongs to with the organizations tool. Use this to discover the org_slug values needed by other org-scoped tools (e.g. alerts, threat_feed), or when the user asks which organizations they have access to.
No parameter schema on file.
List the latest security alerts for a Socket organization with the alerts tool. Requires org_slug — call the organizations tool first if you don't have it. Supports filtering by severity, category, status, artifact type/name, alert type, and repo. Use this to surface supply-chain, vulnerability, quality, license, and maintenance issues across the org's monitored packages. Results are paginat
| Parameter | Type | Required | Notes |
|---|---|---|---|
| org_slug | string | yes | Organization slug, e.g. "my-org" (use the organizations tool to discover this) |
| severity | string | no | Comma-separated severities to include: subset of low,medium,high,critical |
| status | no | Filter to open or cleared alerts | |
| category | string | no | Comma-separated categories: subset of supplyChainRisk,maintenance,quality,license,vulnerability |
| artifact_type | string | no | Comma-separated ecosystems: subset of npm,pypi,gem,maven,golang,nuget,cargo,chrome,openvsx |
| artifact_name | string | no | Filter to a specific package name |
| alert_type | string | no | Comma-separated Socket alert types (e.g. "usesEval,unmaintained") |
| repo_slug | string | no | Comma-separated repo slugs |
| per_page | integer | no | Results per page (default 100, max 5000) |
| cursor | string | no | Pagination cursor — the endCursor from a previous response's metadata |
Look up items in the Socket organization threat feed with the threat_feed tool. Requires org_slug — call the organizations tool first if you don't have it. Returns recently flagged packages (malware, typosquats, obfuscated code, etc.) along with a nextPageCursor for pagination. Use filter to narrow the threat category (default mal for malware), ecosystem to scope to a registry, or `n
| Parameter | Type | Required | Notes |
|---|---|---|---|
| org_slug | string | yes | Organization slug, e.g. "my-org" (use the organizations tool to discover this) |
| filter | string | no | Threat category filter (default mal). Common values: mal (malware), vuln, typ (typosquat), obf (obfuscated), mjo, kes, spy, ano, ucf, ptp, ual |
| ecosystem | string | no | Ecosystem filter, e.g. npm, pypi, gem, maven, golang, nuget, cargo, chrome, openvsx, vscode, huggingface |
| name | string | no | Filter by package name |
| version | string | no | Filter by package version |
| is_human_reviewed | boolean | no | Only return human-reviewed items (default false) |
| sort | no | Sort field (default updated_at) | |
| direction | no | Sort direction (default desc) | |
| updated_after | string | no | ISO timestamp; only return items updated after this |
| created_after | string | no | ISO timestamp; only return items created after this |
| per_page | integer | no | Results per page (default 30, max 100) |
| cursor | string | no | Pagination cursor — the nextPageCursor from a previous response |
List the files published in a package using the package_files tool from Socket. Returns a tree of paths and sizes for any package on a supported ecosystem (npm, pypi, gem, cargo, maven, golang, nuget, chrome, openvsx). Useful for inspecting what a dependency ships before installing it. After calling this, use package_file_contents with one of the paths to read the file's contents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ecosystem | string | yes | Package ecosystem (e.g., npm, pypi, gem, cargo, maven, golang, nuget, chrome, openvsx) |
| depname | string | yes | Package name (e.g., "lodash", "@babel/core", "org.springframework:spring-core", "meta/pyrefly" for openvsx) |
| version | string | yes | Package version |
| artifactId | string | no | Per-version artifact disambiguator (e.g. PyPI filename, Maven artifact id, NuGet asset). Required when an ecosystem ships multiple artifacts per version. |
| platform | string | no | Platform qualifier for ecosystems with per-OS/arch artifacts (e.g. openvsx: 'linux-x64', 'darwin-arm64', 'win32-x64'). |
Read a single file from a package using the package_file_contents tool from Socket. Pass the hash printed next to each entry in package_files output. Returns up to 1 MB of UTF-8 text; binary files return metadata only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hash | string | yes | Blob hash exactly as shown by package_files (the token printed after each file size) |
| path | string | no | Optional file path for display only; does not affect the lookup |
Search a single file from a package for lines matching a JavaScript regular expression. Pass the hash printed next to each entry in package_files output. The file is fetched from Socket once per session and cached, so repeated greps on the same hash skip the network. Returns matching lines with line numbers (grep -n style); binary files are refused. Useful for locating a specific symbol, impor
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hash | string | yes | Blob hash exactly as shown by package_files (the token printed after each file size) |
| pattern | string | yes | JavaScript regular expression. Plain literal strings work too. Anchors and character classes are supported. |
| caseInsensitive | boolean | no | Match case-insensitively (default: false) |
| contextLines | integer | no | Lines of context to show before and after each match (0-5, default: 0) |
| maxMatches | integer | no | Cap on number of matching lines returned (default: 100, max: 500) |
| path | string | no | Optional file path for display only; does not affect the lookup |
- 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 Socket.dev or to call it, at any volume.
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 0.0.20.
No release note was published with this version.
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.
Any signed-in account that does not publish Socket.dev can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.