GitHits
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Sourced, evidence-aware CVE research for CVEs, products, SBOMs and images via NVD, EPSS, KEV, OSV.
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Claude cannot connect Oxiploitability yet
The maker has not listed install details in the MCP Registry yet
ChatGPT cannot connect Oxiploitability yet
The maker has not listed install details in the MCP Registry yet
B · Others in Cybersecurity that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Claude Code cannot connect Oxiploitability yet
The maker has not listed install details in the MCP Registry yet
Cursor cannot connect Oxiploitability yet
The maker has not listed install details in the MCP Registry yet
VS Code cannot connect Oxiploitability yet
The maker has not listed install details in the MCP Registry yet
NVD_API secret envDescriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
GooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 15, 2026
The registry name was verified with the GitHub account abelreqma, which owns the repo
Code last changed 23 days ago
Uses Apache-2.0
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Not checked: only npm and PyPI packages with a version can be checked
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed 23 days ago, and the latest version (0.1.0) reached the registry 23 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Rust on your computer.
In the same category: GitHits, Dependency Management MCP Server, Snyk MCP, Draugr, Spotdb
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.
Sonatype component intelligence: versions, security analysis, and Trust Score recommendations
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Ephemeral data sandbox for AI workflows with guardrails and security
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Oxiploitability is a Rust MCP server for sourced CVE research. It combines NVD vulnerability records, FIRST 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.
This product uses the NVD API but is not endorsed or certified by NVD. EPSS is published by FIRST, KEV by CISA, package advisories by OSV.dev, CVE records by CVE.org and public proof-of-concept links by the nomi-sec/PoC-in-GitHub index.
mcp-name: io.github.abelreqma/oxiploitability-mcp
| Tool | Input | Result |
|---|---|---|
enrich_cve | One CVE or up to 100 CVEs | Combined NVD, EPSS, KEV, CVE.org and PoC data with source errors kept separate. |
nvd_cve | One CVE | NVD description, scores, weaknesses, affected products and references. |
epss_scores | Up to 100 CVEs | EPSS probabilities and percentiles. |
kev_lookup | Up to 100 CVEs | CISA KEV entries and unlisted IDs. |
product_cves | Product name, CPE, package URL or package name | Ranked CVEs, version evidence and a suggested action. |
scan_sbom | SBOM, lockfile, directory or image | Component findings, unchecked items, actions and a new local JSON report. |
poc_search | One CVE | Public repository links from the PoC index; these are unvetted leads. |
Findings name their source and link to its record. nvd-cpe, cve.org-cna and osv:* identify product or package evidence; nvd-description is a lead with confirmed: false. A missing score, KEV entry or PoC is not evidence that a vulnerability is safe or unexploited. Check partial, warnings, needs_verification and not_checked before relying on an answer.
Lookup tools do not write local files. scan_sbom creates a new report without replacing an existing one; an image scan may pull the image through Trivy or Syft if installed. See PRIVACY.md for outbound data and local files.
From this repository, install the native executable with:
cargo install --path . --locked
The executable is normally ~/.cargo/bin/oxiploitability. Rust builds native executables for each operating system and CPU architecture, so use a matching build and its full path in desktop client settings; desktop apps may not inherit your shell's PATH.
An NVD API key is optional. Set NVD_API in the private environment of a CLI client if you have one; do not commit a key to this repository. Without a key, the server uses NVD's lower request limit.
Add this entry to mcpServers in ~/Library/Application Support/Claude/claude_desktop_config.json, preserving other servers, and restart Claude Desktop when convenient:
{
"mcpServers": { "oxiploitability": { "command": "/absolute/path/to/oxiploitability", "args": [] } } }
The optional NVD key field in the packaged MCPB extension has a known Claude Desktop delivery issue for some binary servers. A keyless setup works without it. Release bundles can also be installed as platform-specific .mcpb files through Settings > Extensions > Advanced settings > Install Extension.
claude mcp add --transport stdio --scope user oxiploitability -- /absolute/path/to/oxiploitability
codex mcp add oxiploitability -- /absolute/path/to/oxiploitability
Start a fresh Codex chat after adding the server. If you edit ~/.codex/config.toml instead, use [mcp_servers.oxiploitability] with command = "/absolute/path/to/oxiploitability".
Merge this entry under mcp_servers in ~/.hermes/config.yaml:
mcp_servers:
oxiploitability: command: /absolute/path/to/oxiploitability
Run hermes mcp test oxiploitability to check discovery. In an existing Hermes chat, use /reload-mcp after changing the config.
cargo fmt --check
cargo clippy --all-targets --locked -- -D warnings cargo test --locked python3 -m unittest discover -s mcpb -p 'test_*.py'
Tests use local mock HTTP responses. CI builds the macOS, Linux and Windows bundles before release. To publish, create a v* tag and manually run gh workflow run release.yml --ref vX.Y.Z for that tag; the workflow verifies the staged assets before publishing to crates.io and the MCP Registry. Do not run it until the client installations have been checked.
Licensed under MIT or Apache-2.0, at your option. See LICENSE-MIT and LICENSE-APACHE.