cleanup
7 registry entries were observed exposing a tool named cleanup — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,336 of 40,577 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v3.8.3↓ 2k/wk★ 21k
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
compoundengineeringcollection - v0.4.2★ 5
Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP
ClaudeCursorCopilotGeminimcp - v3.8.0↓ 27k/wk★ 1k
MCP server for interacting with Kubernetes clusters via kubectl
ClaudeCursorCopilotGeminimcpkubernetesclaudeanthropickubectlinfrastructure - v0.4.6↓ 356/wk★ 6
Code-aware browser testing for AI coding agents. Reads your codebase so tests use real routes and field names, runs them in Playwright, remembers what broke, and reports what your last change fixed or regressed. No LLM calls inside. MCP server for Claude
ClaudeCursorCopilotGeminitestingbrowser-testingai-testingautomated-testingplaywrightmcp - ★ 1k
MCP Server for kubernetes management commands
infrastructurekubernetesmcpserver - v0.3.11★ 3
Agent reasoning, memory, and token-optimized context for AI applications.
ClaudeCursorCopilotGeminimcp - v0.2.11★ 1
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
ClaudeCursorCopilotGeminimcp