registry / breakpoint-mcp / 1.12.0

breakpoint-mcp@1.12.0

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

AI Security Review

scanned 5d ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User runs `breakpoint-mcp init --client <client>` or invokes its MCP tools.

Impact

A user-requested setup can register `npx -y breakpoint-mcp` with supported AI clients and grant that server its documented Godot project capabilities.

Mechanism

Explicit MCP-client configuration mutation plus Godot project/process automation.

Rationale

Source inspection confirms an explicit-user-command AI-client configuration mutation and powerful project automation, but no covert or install-time malicious chain. Treat as a warning-level agent capability risk rather than a publish block.

Evidence

package.jsondist/index.jsdist/cli/init.jsdist/cli/clients.jsdist/cli/github.jsdist/tools/processes.jsdist/stdio.jsaddon/breakpoint_mcpproject.godot.vscode/mcp.json~/.cursor/mcp.json~/.codeium/windsurf/mcp_config.json

Network endpoints2

api.github.com

breakpoint-mcp@1.12.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code