mcpField
K
Kernel CVE MCP Server

Kernel CVE MCP Server

Local
github.com/mattfosterDeveloper Tools1Updated 65w ago

About Kernel CVE MCP Server

Kernel CVE MCP Server stores the Linux kernel CVE list in SQLite and provides a basic way to query it. It is intended for users who need to look up or search kernel CVE records.

Key features

  1. 01Download kernel CVE list to SQLite
  2. 02Retrieve CVE information
  3. 03Search kernel CVE records

Use cases

  1. 01Look up details for a kernel CVE
  2. 02Search kernel CVE records

MCP support

The stdio MCP server exposes `get_kernel_cve_info` and `search_kernel_cve_info` tools to MCP clients.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

Kernel CVE MCP Server

This clones the linux kernel CVE List git repo, into an sqlite database and then allows querying this DB with a really basic MCP server.

See: https://lore.kernel.org/linux-cve-announce/_/text/mirror/ for details.

Commands

  • kernel-list-to-sqlite - Download the Kernel CVE list into a temporary dir and save the contents into an sqlite database.
  • stio-mcp - stdio MCP server which provides the get_kernel_cve_info and search_kernel_cve_info tools.

Config

You need to specify the location of the DB file, so use something like this:

 {
  "mcpServers": {
    "kernel-cve-info": {
      "command": "/Users/mpf/Projects/kcve/stdio-mcp",
      "args": ["-db", "/Users/mpf/Projects/kcve/commits.db"]
    }
  }
}

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.