Blitz Strike
MCP ServerA penetration-testing methodology delivered as one MCP server: BLITZ maps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE live-verifies every finding before it is reported.
- mcp-server
- security
- pentest
- methodology
Official reference MCP server for read/write access to the local filesystem.
Provides Models with controlled access to files and directories, with configurable allowed paths and read/write permissions.
The default first MCP server for local-agent work: codebase exploration, bulk refactors, writing reports into a folder, or any task where Claude needs real files under your control. Pair with git-mcp so file changes stay versioned.
Add to .mcp.json under mcpServers.filesystem:
{
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/projects", "/tmp/claude-scratch"]
}
Every argument after the package name is an allowed directory; only those paths are reachable.Safety equals your allow-list: mounting $HOME defeats the purpose, so scope to project directories plus a scratch dir if writes are needed. There is no undo inside the server — destructive writes are permanent, so keep everything under version control.
Repository
modelcontextprotocol/serversCharted
A penetration-testing methodology delivered as one MCP server: BLITZ maps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE live-verifies every finding before it is reported.
Red Hat's "ripgrep for AI context" — a C++23 zero-dependency CLI that also speaks MCP.
One shared session memory for 25+ coding agents — Claude Code, Codex, and Cursor finally remember the same project.