guardrails
27 servers · 790★ total
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
[L0 CONSTITUTION] arifOS — constitutional MCP kernel. Law, identity, F1–F13, VAULT999. Judges but never executes. DITEMPA BUKAN DIBERI.
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wraps any MCP, 20 included (Postgres, MySQL, MongoDB, GitHub, Stripe, Snowflake, etc.). 84% fewer tokens, ~3x faster, holds PII leaks. AGPL or commercial.
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
VHK — AI 코딩 세션을 목표·증거·기억·규칙으로 묶는 한국어 CLI. 규칙 동기화, MCP 35 tools, verify/review/preflight 게이트.
Privacy guardrails for Spring AI: request-scoped PII tokenization and least-privilege disclosure across model/tool calls, with Presidio and JVM-local OpenNLP.
Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.
A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.
Official TypeScript/JavaScript SDK for Cognipeer Console — OpenAI-compatible chat, batch, realtime voice, embeddings, RAG, MCP, agent tracing, and guardrails for multi-tenant AI products.
MCP server for PBPK modeling workflows (simulation control + PK analytics).
Evidence federation MCP server for the EPA CompTox API
MCP server for Adverse Outcome Pathway (AOP) discovery, semantics, and draft authoring.
A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.
🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
Open-source MCP gateway: 0.02ms overhead, 46K+ RPS cache hits, auth, guardrails, plugins, multi-server routing. 1341 tests.
An AI organism - the human-AI interface layer. A safety reflex that refuses known lethal actions even when the model is fooled, and a memory that only keeps what actually worked. For code, research, writing, or a fleet of agents. 100% local.
Stop AI agents from doing dangerous things through MCP. Wraps any MCP server with allow/block/hold-for-approval guardrails.
Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.
MCP server that adds a fail-closed quality gate and hash-chained receipt ledger to any AI agent workflow.
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.
Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.
MCP server for OECD QSAR Toolbox workflows with structured outputs and PDF reports.
Dual-protocol gateway: 62 MCP tools + A2A Protocol agent (82/82 TCK intentional) in a single governed runtime