mcpField
M
MCP Server For OSV

MCP Server For OSV

Local
github.com/EdenYavinSecurity2Updated 79w ago

About MCP Server For OSV

MCP Server For OSV exposes OSV database queries for security and development workflows. It helps users look up package CVEs, affected versions, and fixes.

Key features

  1. 01Query CVEs by package and version
  2. 02List affected versions for a CVE
  3. 03Find fixed versions for a CVE
  4. 04List supported ecosystems

Use cases

  1. 01Check a dependency for known CVEs
  2. 02Identify versions affected by a CVE
  3. 03Find versions that contain a vulnerability fix

MCP support

It provides MCP tools that query the OSV Database API for package vulnerabilities, affected and fixed versions, and supported ecosystems.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"osv-mcp-edenyavin": {
"command": "npx",
"args": [
"-y",
"@smithery/cli"
]
}
}
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Server For OSV

A lightweight MCP (Model Context Protocol) server for OSV Database API.

Example:

demo


Tools Provided

Overview
namedescription
query_package_cveList all the CVE IDs for a specific package. Specific version can be passed as well for more narrow scope CVE IDs.
query_for_cve_affectedQuery the OSV database for a CVE and return all affected versions of the package.
query_for_cve_fix_versionsQuery the OSV database for a CVE and return all versions that fix the vulnerability.
get_ecosystemsQuery the MCP for current supported ecosystems.
Detailed Description
  • query_package_cve

    • Query the OSV database for a package and return the CVE IDs.
    • Input parameters:
      • package (string, required): The package name to query
      • version (string, optional): The version of the package to query. If not specified, queries all versions
      • ecosystem (string, optional): The ecosystem of the package. Defaults to "PyPI" for Python packages
    • Returns a list of CVE IDs with their details
  • query_for_cve_affected

    • Query the OSV database for a CVE and return all affected versions.
    • Input parameters:
      • cve (string, required): The CVE ID to query (e.g., "CVE-2018-1000805")
    • Returns a list of affected version strings
  • query_for_cve_fix_versions

    • Query the OSV database for a CVE and return all versions that fix the vulnerability.
    • Input parameters:
      • cve (string, required): The CVE ID to query (e.g., "CVE-2018-1000805")
    • Returns a list of fixed version strings
  • get_ecosystems

    • Query for all current supported ecosystems by the MCP servers.
    • Return a dict with the key being the ecosystem name and the value the programming language / OS.

Prerequisites

  1. Python 3.11 or higher: This project requires Python 3.11 or newer.

    # Check your Python version
    python --version
    
  2. Install uv: A fast Python package installer and resolver.

    pip install uv
    

    Or use Homebrew:

    brew install uv
    

Tested on

  • Cursor
  • Claude

Installation

  1. Via Smithery:
npx -y @smithery/cli install @EdenYavin/OSV-MCP --client claude
  1. Locally:

    1. Clone the repo: https://github.com/EdenYavin/OSV-MCP.git
    2. Configure your MCP Host (Cusrsor / Claude Desktop etc.):
{
  "mcpServers": {
    "osv-mcp": {
      "command": "uv",
      "args": ["--directory", "path-to/OSV-MCP", "run", "osv-server"],
      "env": {}
    }
  }
}


Leave a review on VibeApp if you enjoyed it :)!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.