Scans supported project manifests for OSV vulnerabilities, opens a review dashboard, and applies confirmed dependency fixes.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
This server is confirmed live โ we successfully called its tools/list endpoint directly (see the verified badge above). We haven't yet sandbox-tested the stdio install command below specifically, which is a separate, ongoing check.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Osv Ui.
scan_projectScan a project directory for CVE vulnerabilities. Automatically detects npm, Python, Go, Rust, Java/Maven, PHP/Composer, and Ruby/Bundler manifests. Queries live CVE data from OSV.dev. Returns structured vulnerability report with severity counts, risk score, and fix recommendations. Use this as the first step before open_dashboard or apply_fixes.
open_dashboardLaunch the osv-ui visual dashboard in the browser for human review. This is the HUMAN-IN-THE-LOOP step โ always offer this before applying fixes. The dashboard shows full CVE details, severity charts, and the upgrade guide. Returns the dashboard URL. If already running for this path, returns existing URL.
get_fix_commandsGet the safe upgrade commands for vulnerable packages WITHOUT executing them. Use this to show the user what will be changed before calling apply_fixes. Returns a list of commands grouped by ecosystem (npm, pip, go, cargo, Maven, Composer, Bundler).
apply_fixesExecute package upgrade commands to fix CVEs. IMPORTANT: This is a DESTRUCTIVE action that modifies package files. ALWAYS call get_fix_commands first and confirm with the user before calling this. Returns the command output for each fix applied.
toan203/osv-ui MCP server connects an MCP-compatible client to a local dependency vulnerability audit workflow. It scans project directories and detects supported package manifests for npm, Python, Go, Rust, Java/Maven, PHP/Composer, and Ruby/Bundler projects. The scan uses OSV.dev to look up current vulnerability data and returns a structured report containing vulnerability details, severity totals, a risk score, and suggested fixes.
The server is intended for audits where an agent should collect findings without immediately changing files. It can start the osv-ui browser dashboard for a person to inspect the results, including CVE details, severity charts, and upgrade guidance. This human review step is important before changing dependency files.
The scan tool reads dependency metadata from project files such as lockfiles, requirements files, pyproject.toml, pom.xml, composer.json, and Ruby manifest files. It sends package information to OSV.dev for vulnerability matching. The README describes the service as running locally, with no signup or API key required; project code remains on the local machine while vulnerability lookups use the OSV.dev service.
The workflow is deliberately split into discovery, review, and modification:
scan_project to find vulnerabilities and recommended versions.open_dashboard to provide a browser-based review interface.get_fix_commands to show the package commands that would be run.apply_fixes.apply_fixes is destructive: it executes upgrade commands and modifies package files. The server returns command output for each applied fix. If the dashboard is already running for the requested path, open_dashboard returns its existing URL.
toan203/osv-ui MCP server can be configured as a local stdio server with the osv-ui-mcp npm package. The documented setup uses npx with the -y option:
The README identifies Claude Desktop and Cursor as supported AI-agent clients. No API key, account, or other credential is required. Vulnerability data comes from OSV.dev, which aggregates sources including NVD, GitHub Advisory, PyPI Advisory, npm advisories, RustSec, and the Go vulnerability database.
scan_project: Detect supported manifests and return vulnerability findings, severity counts, risk score, and fix recommendations.open_dashboard: Launch the local visual dashboard and return its URL for human review.get_fix_commands: Produce package upgrade commands without executing them, grouped by ecosystem.apply_fixes: Execute approved upgrade commands and return their output.The supported package ecosystems include npm, pip, Go, Cargo, Maven, Composer, and Bundler. The broader osv-ui project also provides command-line reporting options, but the MCP listing specifically exposes the four tools above.
toan203/osv-ui MCP server depends on the supported manifest formats and OSV.dev lookups for its vulnerability data. Use --offline only with the command-line application; the listed MCP tools are described around live OSV.dev scanning. Fix application changes package files, so an agent should present the generated commands and obtain confirmation before execution. The dashboard is a local browser interface rather than a hosted review service.
Factual signals from GitHub, npm, and our automated checks โ not a rating.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/toan203-osv-ui)<a href="https://allmcps.com/mcp/toan203-osv-ui"><img src="https://allmcps.com/api/badge/toan203-osv-ui?style=directory" alt="Osv Ui on AllMCPs" /></a>