2,939 packages matching “destructive”
@automatey-org/mcp
v0.1.3 · 1 month ago
Provider-agnostic MCP helpers for the Vercel AI SDK: a Streamable-HTTP MCP client and a buildMcpToolSet() that exposes MCP tools as AI SDK tools with destructive-tool gating and call/result callbacks.
No known vulnerabilities
orangerail
v0.1.5 · 2 days ago
Generate an MCP server from your Prisma schema — typed per-model tools instead of execute_sql, destructive writes gated behind human approval, every action on an audit log. Plus the operator surface: approvals, audit verify, status, studio.
No known vulnerabilities
@aegiskit/dast
v0.0.3 · 29 days ago
Dynamic application security testing for Aegis — confirms vulnerabilities against YOUR OWN running Next.js/Supabase app via bounded, non-destructive HTTP probes, and correlates them with static findings.
No known vulnerabilities
@robhowley/pi-yolo-seatbelt
v0.3.0 · 1 month ago
Keep the YOLO workflow but avoid bash catastrophe with configurable guardrails for destructive commands.
No known vulnerabilities
obj-merge
v0.0.4 · 11 years ago
non-destructive extend
No known vulnerabilities
@mizchi/tree-utils
v0.2.1 · 7 years ago
Non-destructive tree utils.
No known vulnerabilities
@molecule/app-danger-zone-react
v1.0.1 · 3 days ago
DangerZoneSection + ConfirmDialog for destructive actions (delete account, reset, revoke)
No known vulnerabilities
@pi-vault/pi-guardrails
v0.1.0 · 1 month ago
Pi extension for damage control - prevents dangerous operations, protects env files, gates destructive commands
No known vulnerabilities
@neabyte/terminal
v0.2.0 · 2 months ago
Secure command sandbox preventing AI destructive code deletions
No known vulnerabilities
breakpoint-mcp
v1.73.4 · 1 day ago
MCP server exposing Godot to AI coding assistants over the Model Context Protocol — developed and tested with Claude — across four planes (CLI, live editor, LSP+DAP, runtime) with elicitation-gated destructive tools, long jobs on the formal MCP task model
No known vulnerabilities
@xultrax-web/agent-memory-mcp
v0.15.1 · 1 month ago
Codify how you work. Every AI tool obeys. Markdown rules + cross-tool companion files (AGENTS.md/CLAUDE.md/.cursor/rules/.gemini) + Compliance Receipts for protocol-level enforcement of destructive ops. Reference implementation of CRP 1.0. Works on every
No known vulnerabilities
react-native-image-crop-data
v0.1.1 · 1 day ago
Non-destructive image cropping for React Native: store crop transforms as data, replay them on any renderer, and rasterize the source image only on explicit export.
No known vulnerabilities
orc-brain
v1.0.0 · 26 days ago
A local orchestrator brain for Claude Code sub-agents — autonomous within bounds, observable always, never destructive in production.
No known vulnerabilities
ndparser
v0.0.4 · 10 years ago
Non-destructive JS parser.
No known vulnerabilities
@omni-pt/omnimemory-overlay
v0.2.4 · 3 months ago
Non-destructive external long-term memory overlay for OpenClaw.
No known vulnerabilities
@sureshsankaran/destructive-check-plugin
v1.1.0 · 5 months ago
OpenCode plugin that detects and requires user permission for destructive commands before execution
No known vulnerabilities
openclaw-safeshield
v0.1.4 · 2 months ago
Security plugin for OpenClaw — blocks destructive commands
No known vulnerabilities
create-issflow
v1.7.0 · 1 month ago
Scaffold the iStartSoftFlow AI-coding workflow into a project. Stack-agnostic, tool-agnostic (Claude Code, Codex, Cursor, Gemini, Aider), non-destructive.
No known vulnerabilities
uri-string-parser
v1.0.0-beta.2 · 8 years ago
A non-destructive parser for URI and URL strings.
No known vulnerabilities
@lofa199419/ui-whatsynaptor
v2.0.4 · 2 months ago
Inject non-destructive Control UI branding overlays for OpenClaw
No known vulnerabilities