MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
osv-mcpgithub.com/arterorx/osv-mcpupdated this year
MCP server for Claude — audit open-source dependencies for known vulnerabilities
MIT ★ 1 -
Scan open-source software packages against the Google OSV distributed vulnerability database for known CVEs. MCP Server & Python SDK.
MIT ★ 1 -
Dependency vulnerability scanner over OSV.dev with CISA KEV actively-exploited flags. No API key.
-
MCP server for PyPI: search packages and audit dependency trees against OSV vulnerability data before an agent suggests them.
MIT ★ 3 -
Read-only MCP server for vulnerability research with OSV, NVD, KEV, EPSS, and deps.dev. Source context and explicit pagination.
MIT -
MCP server that checks npm, PyPI, Go, crates and more against OSV.dev for known vulnerabilities and malware. Free tier, then pay per call via x402.
MIT -
MCP server that tells your AI agent which vulnerabilities to fix first: OSV.dev + EPSS + CISA KEV combined into one explainable priority score.
MIT -
Claude Code plugin: security news and alerts for the tech your projects actually run on (Composer/npm packages, runtimes, OS packages), from vendor feeds, CISA, OSV and NVD.
GPL-3.0 ★ 1 -
Dependency vulnerability and malicious package scanner for AI agents and MCP: check package.json, package-lock.json, requirements.txt, go.mod, Cargo.lock for known CVEs (GHSA, OSV) and malware before npm install. Free MCP server; full advisories via x402
npm MIT -
Dependency risk visualizer — Scorecard + OSV + typosquat + maintainer signals
NOASSERTION -
Audit a project dependencies for known vulnerabilities and outdated versions from its lockfiles (transitive included), via OSV.dev and MCP.
MIT -
MCP server for CVE/config remediation orchestration: SSH inventory, OSV/NVD lookups, CIS/DISA STIG-mapped Ansible playbook suggestions.
★ 1 -
Dependency vulnerability checker for AI assistants: a CLI, an MCP server and a local dashboard. Scans Rust, JS/TS, PHP, Go and Python lockfiles against OSV, ranked by CISA KEV and EPSS.
MIT ★ 1 -
Hourly answer to "does this new vulnerability affect what I actually run?" SSH inventory, OSV/KEV/Chrome matching, read-only agent triage, and an MCP server for your coding agent.
MIT -
voraxx-mcp-servergithub.com/bharat3645/voraxx-mcp-serverupdated this year
Stdlib-only Python MCP server with three security tools: CVE lookup via OSV.dev, host exposure via Shodan InternetDB, and orchestration of a locally installed Nuclei scanner. No exploit code bundled; 19 tests; alpha companion to Voraxx.
MIT -
@mcpskillsio/servergithub.com/bebravebekind/mcpskills-serverupdated this year
Use the MCPSkills pre-install trust layer from Claude Code, Cursor, or any MCP client. Accepts GitHub repos, npm packages, Smithery URLs, and OpenClaw skills. 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence), safety scanning, OpenClaw frontmatte
npm MIT -
Upgrade intelligence for AI coding agents: what changes between your installed and target version (changelog, breaking changes, the files you import it from), a pre-install verdict on each bump, vulnerability scanning at osv-scanner parity across npm/pnpm
npm Apache-2.0 -
Rust MCP server for sourced CVE research, combining NVD records, EPSS probabilities, CISA KEV entries, OSV package advisories, CVE.org records and a public proof-of-concept index. It can also check supported SBOMs, lockfiles, project directories and container images.
Apache-2.0 ★ 1 -
Explain any lockfile change: bumps release-verified against 22 registries, vulns (OSV), ages, deprecations, typosquats, integrity tampering — 61 formats incl. pdm.lock, vcpkg, mise.lock, build.gradle, pom.xml, go.sum, GitHub Actions, GitLab CI, Dockerfiles, Kubernetes, Helm, SBOMs. CLI + CI gate + MCP server + playground. By an AI agent.
MIT ★ 1 -
MCP servers for everyday development and security checks: OSV vulnerability lookup, security header grading, JWT decoding and verification, regex testing with ReDoS detection, cron explanation, JSON Schema validation, OpenAPI and Dockerfile linting, read-only git insights and llms.txt generation. TypeScript, stdio, zod-validated, no telemetry.
MIT ★ 1 -
MCP server that checks public IPs, domains, CVEs and software versions for confirmed vulnerabilities and exposure (NVD, CISA KEV, EPSS, OSV.dev, Shodan and more), with Ubuntu/Debian backport checks and a report checker. Works with Claude, Cursor and VS Code; no LLM key needed.
MIT ★ 1 -
Security layer for AI agents: real-time interception of pip/npm/cargo/gem/go installs via Hermes & OpenClaw plugins, Claude Code/Codex hooks, MCP, shell guard, PATH shim, execve, and index proxy. Checks CVEs (OSV/NVD/GitHub), typosquats, malware, licenses, provenance, trust, lockfile hashes. Offline mirror, hash-chained audit, SBOM/SARIF.
MIT ★ 4 -
AI Dependency Security MCP Server
MIT -
Cybersecurity-MCPgithub.com/LiamTCollins/Cybersecurity-MCPupdated this year
A tool to add to an agent's repertoire to improve security of AI created apps and sites.
Apache-2.0 -
closeread-verifygithub.com/FreeGuy-AI/closeread-verifyupdated this year
Verified dependency audit as an MCP tool: a checked-against-the-installed-version verdict any AI agent can call, not a raw scan.
NOASSERTION -
LineBreak security gate at the git/CI boundary: dependency CVE scan + AI SAST, human-approved overrides, git-native audit records
pypi Apache-2.0 -
Install gate for AI coding agents: blocks malicious, hallucinated and typosquatted packages (npm, PyPI, crates.io, Go) before Claude Code installs them. Hook + MCP server + CLI.
MIT -
package-intelgithub.com/adam121393/package-intelupdated this year
Package & dependency intelligence for AI coding agents. Free npm, PyPI and crates.io health, vulnerability, dependency-graph and download data over MCP; consolidated risk scores paid per-call in USDC via x402.
MIT -
Local security check for AI-built apps: leaked keys, open Supabase/Firebase rules, risky packages — then hand fixes to your AI. AI로 만든 앱의 키 노출·접근 규칙·취약 패키지를 로컬에서 검사합니다. 本地检查 AI 生成应用的密钥泄露、开放的访问规则和有风险的依赖包。
npm Apache-2.0 -
@fairquery/agent-trust-mcpactive
Fairquery Agent Trust & Data Safety MCP server: PII/secret redaction, email validation, sanctions screening, dependency checks and a local MCP server pre-check for AI agents. Free local tools + optional paid Apify-backed deep tools.
npm MIT -
Proof that a change got the checks your repository asks for, whoever made it: AI coding agents (Claude Code, Cursor, Codex, Copilot, any MCP agent) and people, held at the commit and verified again in CI with signed in-toto attestations.
npm Apache-2.0