MCP servers for guardrails

Typed 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

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Anti-hallucination gate for AI coding agents — 8 MCP tools catch invented APIs (17 languages), fake "all tests pass" claims, and slopsquatting packages before they ship. Zero-dependency Agent Plugins

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

Zero-dependency System One decision harness: 5 semantic gates saving frontier AI agent tokens on trivial errors & doom loops. Python + TypeScript + Rust. MCP-compatible.

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

x402 risk-check provider: signed pre-payment verdicts — OFAC, phishing feeds, transaction simulation, drainer-kit code, and our own EIP-7702 kit watch (poisoners, sweepers). $0.001 per check with prep

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

A Claude Code plugin that checks every file and shell call an AI agent makes, fixes what it safely can, and tells the agent how to fix the rest. Windows and macOS.

Multi-persona deliberation and Bayesian weighted consensus engine resolving complex agent decision ambiguities

Pre-commit diff safety scanner preventing destructive shell commands, API token leaks, and disk corruptions

Multi-turn autonomous agent trajectory evaluator measuring step redundancy and tool choice efficiency

Fault-tolerant tool execution circuit breaker detecting cascading upstream errors and triggering fallback routing

Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs

Fault-tolerant tool execution circuit breaker detecting cascading upstream errors and triggering fallback routing

Pre-commit diff safety scanner preventing destructive shell commands, API token leaks, and disk corruptions

Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs

Multi-persona deliberation and Bayesian weighted consensus engine resolving complex agent decision ambiguities

Multi-turn autonomous agent trajectory evaluator measuring step redundancy and tool choice efficiency

Djævin: calibrated local-first decision layer with a Devin ACP backend - no API key needed

Privacy guardrails for Spring AI: request-scoped PII tokenization and least-privilege disclosure across model/tool calls, with Presidio and JVM-local OpenNLP.

Security & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot starter.

A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.

🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.

Anti-hallucination guardrails for AI coding agents - hybrid Skill + MCP server (6 tools) that verifies code before it is marked done. Works with Claude Code, Cursor, VS Code, Copilot.

Intent firewall for AI agents — NVIDIA Nemotron checks every tool call against the user's goal and blocks prompt-injection hijacks before they run.

Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca