A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.
View on GitHub ↗Homepage ↗A three-stage guardrail agent for LLM-powered coding assistants.
Sentinel sits between an LLM agent and its execution environment, reviewing every proposed action before it runs. It integrates with tools like Claude Code, Cursor, and CodeX via the Model Context Protocol (MCP), acting as an always-on safety layer that can block destructive commands, flag scope creep, and maintain a full audit trail of every decision.
Supports both Stdio (local process) and SSE (web endpoint) MCP transports for maximum compatibility.
Autonomous LLM coding agents can execute shell commands, modify files, push to remote repositories, and make network requests. This power comes with real risk: a single poorly-scoped prompt or a hallucinated action can cause data loss, expose credentials, or make irreversible changes to a production system.
Existing solutions are binary — either the agent runs everything without review, or a human must manually approve every step. Neither scales.
Sentinel implements a multi-stage decision pipeline that handles the full spectrum from obviously safe to dangerously risky actions, using the fastest and most appropriate tool at each stage:
Stage 1 — Rules Engine: Pattern matching on a configurable YAML ruleset. Handles unambiguous cases (recursive deletes, credential exposure, root-level writes) in microseconds with zero network dependency.
Stage 2 — Trained Classifier: A TF-IDF vectorizer and Logistic Regression classifier trained on a labeled dataset of agent actions. Runs in milliseconds, entirely offline, and produces an explainable risk score with confiden
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/fncreator22--sentinel-mcp.html)
Self-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.
CacheCarti/dmoera-mcpdMoERA Creator Studio MCP Server: build, backtest, and deploy crypto trading strategies via AI agents
TeodorMCP/universal-connector-mcpUniversal MCP server: connect any OpenAPI/Swagger, GraphQL, gRPC or SOAP API to AI agents. Security-first, local, token-efficient. Any API. One server.
kenb38291-tech/fastmcp-sqliteProduction-grade, token-optimized FastMCP SQLite Server with sub-millisecond O(1) schema discovery, opcode execution watchdog, and fuzzy self-healing.
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
SysikNagibator/AiPCGive the agent "this" and he gets a real PC.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.