Vibe Coding DiscoverDoberman-Core
View on GitHubYour AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
Doberman intercepts coding-agent tool calls through MCP proxies and host hooks, then allows, requires approval for, or blocks each action before execution. It provides policy controls and an auditable decision log.
Use Cases
Block destructive commands before executionRequire approval for sensitive tool callsPrevent secret exfiltration by coding agentsEnforce policies across MCP tool serversAudit AI agent actions
Built With
- Language
- Python
- Frameworks
- MCP · Pydantic
Tags
agent security · runtime guardrails · authorization · tool-call filtering · MCP proxy · human approval · audit logging · coding agents