Doberman-Core MCP Server
DobermanCore/Doberman-Core
[](https://agentrank-ai.com/tool/DobermanCore--Doberman-Core/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
DobermanCore/Doberman-Core is a Python tool licensed under Apache-2.0. Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute. Topics: agent-security, ai-agents, ai-safety, authorization, guardrails, llm, llm-security, mcp, python, security.
Ranked #2424 out of 24846 indexed tools.
In the top 10% of all indexed tools.
Has 30 contributors.
Ecosystem
Score Breakdown
280 stars → growing community
Last commit 1mo ago → moderate activity
153/228 issues closed → decent issue management
30 contributors → active community
No dependents → no downstream usage
49 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/DobermanCore--Doberman-Core/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/DobermanCore--Doberman-Core/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/DobermanCore--Doberman-Core" alt="AgentRank"></a> Matched Queries
From the README
<div align="center"> # Doberman **Adaptive Authorization & Runtime Guardrails for AI Coding Agents** Your AI coding agent can run `rm -rf` on your repo, leak your API keys, or get tricked by hidden instructions into leaking data on its own, with no undo. Doberman is the guard dog on the execution path. It stops the dangerous call before it runs. </div> <p align="center"> <br> <em><code>doberman demo</code> against the live dashboard (<code>doberman dash</code>): five attacks blocked as they happen, then a human denies a high-risk approval.</em> </p> > A guardrail that isn't on the execution path can only advise. Doberman sits between the agent and its tools, through a transparent **MCP proxy** or **host hook** (MCP: Model Context Protocol, the standard interface between an agent and its tools; a hook is code the host runs automatically around a tool call), and turns every action into an explicit, auditable decision. Every tool call gets exactly one verdict, decided beforeRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.