- Conduid
- Marketplace
- #guardrails
MCP servers tagged guardrails
304 live MCP servers tagged "guardrails", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with guardrails.
Bridge
REST bridge to the MCP ecosystem, powered by mcp-use
Jenkins MCP Server
Secure-by-design Jenkins MCP server with runtime guardrails. Minibridge integration for Rego/HTTP policy enforcement, Jenkins-aware prompt-injection guardrails, destructive tools…
Fuse
A local firewall for AI agent commands
Agent Gateway
Standardized gateway for AI agent discovery, custom contracts, and secure auditing with Guardrails
AI Engineer
AI engineering portfolio with Next.js demos for LLMs, RAG, vector search, embeddings, agents, MCP, guardrails, observability, prompt engineering, and token economics.
Headroom
More human oversight can make an AI agent less safe. Headroom is a human-in-the-loop firewall for coding agents that measures when to trust the human: oversight as resource alloca…
Hydra
Real-time AI threat interception. Blocks CVE-mapped attacks, poisoned configs, and destructive terminal commands before execution.
Veratum
"Veratum - The production AI coding harness & skill for Antigravity, Claude Code, Cursor, and Windsurf. Prevents AI hallucinations, scope creep, and untested code."
Hello Agent
From-scratch TDD LLM agent framework: tool-calling, RAG, MCP, multi-agent, evals, guardrails, FastAPI+Docker
Taintgate
🚧 A policy gate for AI agent tool calls, with provenance tracking. Blocks what prompt-injection classifiers miss: where an instruction came from.
Agent Shield
为 LLM Agent 提供安全防护与审计框架，防御 MCP 投毒攻击，支持 HITL (Human-in-the-loop) 与审计调度。
Verdict Core
Control plane for AI coding agents: decides which models may run each task, recovers from rate limits and timeouts, sends work to a separate reviewer model, and writes verifiable…
Spring AI Playground
A collection of focused, self-contained Spring AI 2.0 + Spring Boot 4.1 demo projects — ChatClient vs ChatModel, structured output, custom advisors, guardrails, tool search, strea…
Leash
Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.
Mill
Guardrailed agentic workflows, on your desktop — agents and humans compose automations; a guardrail previews and gates every action before it happens. Single-binary Go + React (Wa…
Agent Action Gate
Deterministic policy gates for AI agent tool calls: allow, deny, or require human approval.
Agent Guardrail
Policy enforcement and permission testing for AI agents. Mock enterprise APIs, simulate synthetic user consent, and block unauthorized data access before deployment.
Orion
🎯Building a Production LLM Application
Loopspec
MCP server + CLI that makes AI coding assistants smarter — persistent memory, drift detection, goal tracking, dependency graphs. Zero API calls. 125 tests. 42 tools.
Bayesoutputgate
Calibrated output validation with the Bayes Factor: weigh per-dimension quality scores into a pass, fail, or escalate decision on the Jeffreys scale, not an arbitrary threshold. Z…
Agentic Trader
Autonomous trading agent with hard, deterministic guardrails — headless Claude Code + broker MCP; the strategy is a pluggable example.
Harness Cook
🧑🍳 Harness Engineering-Agent 治理集成总线 — 为 Claude Code / Copilot CLI / Hermes / Cursor / OpenAI 等 AI Agent 提供声明式配置、一键部署、可观测的管控能力。Hooks 定约束，Skills 定步骤，Agents 定角色。
Federation Watchtower
Federation Watchtower is a developer tool that makes autonomous work visible before it becomes expensive.
Awesome Verified Agents
Tools that produce evidence about what an AI agent actually did — gates, attestation, output verification, benchmarks. Inclusion bar: name the artifact a human can inspect later.
Safetydrift
First open-source implementation of the SafetyDrift framework (arXiv:2603.27148) — predicts when individually safe AI agent actions compound into a safety violation using Markov c…
Agent Chaperone
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.
HR Supervisor Coaching
MCP Server | AI GPT | Approved HR policies and real-world operating scenarios to practice difficult conversations and choose appropriate next steps.
AI LLM Automation Systems
AI/LLM automation reference: RAG, tool calling, human review, evals, observability, safety gates, and local deterministic samples.
Watchlight De
Watchlight Developer Edition for Agent Runtime Governance - AI Security - AI Agent Security
Agent Development Kit
Typed, provider-neutral Python ADK for production AI agents with A2A, MCP, gateways, guardrails, deterministic tests, and pluggable model providers.
AI Shield Py
Python LLM security middleware: prompt-injection, PII, tool-policy, cost-budget, audit. Port of ai-shield-core (TS).
Intercepter
Transparent proxy + enterprise gateway for MCP: audit logging, tool allow/deny policy, secrets/PII redaction, and OpenTelemetry for every AI agent <-> MCP tool call.
Support Copilot
Customer-support AI agent: LangGraph supervisor + specialist handoffs, deterministic tools, human-in-the-loop refunds, guardrails, embedded eval gate, Langfuse traces, MCP. Fully…
Naukri AI Recruitment Agent
Production-minded Recruitment & HR support agent built with LangGraph, RAG, tool calling, memory, guardrails, MCP, FastAPI, evaluation, and resilience patterns.
Deterministic Agent Gatekeeper
Determinism you can prove for AI agent tool calls: a pure decision core whose every verdict re-derives hash-exact from its record.
Purse
Purse is the enforcement point your agent's payments pass through. Route every spend through it. Set limits, require human approval over a threshold, and get a tamper-evident log…
Smb Products
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
MermaidGuard
Zero-dependency deterministic linter, guardrail & conservative repair engine for Mermaid diagrams in Markdown & CI/CD. Built-in MCP server for AI agents.
Spend Guard
Wrap any MCP server with a hard spend cap, per-tool rate limits, a wall-clock timeout and a kill switch. MCP has no built-in rate limiting - this is the drop-in stdio proxy that a…
Sre Harness
A minimal, runnable reference harness for SRE agents: tool orchestration, verification, memory, guardrails, and observability in one ~40-line loop. Agent = Model + Harness.
Model Sherpa
Stop hallucinated tool calls, break looping behaviour, and keep secrets out of your context window — zero-config guide-rails for Hermes Agent.
Regrails
Policy-as-code for FERPA + Title IV: a deterministic guardrail that decides before any LLM speaks. Risk-tiered, citation-faithful, with an MCP server, OSCAL/SARIF exports, a GitHu…
Agentobs
Stop your AI coding agent before it overspends. Budget limits, guardrails and cost tracking for Claude Code - local-first, no account.
Dsh Jev Verify
Jev (TypeSafe System One) for DeepSeek Harness: five verdict tools - jev_decision, jev_choose, jev_overview, jev_guard_status, jev_verify - with in-chat views, real system-prompt…
TGS 2024042309 Develop AI Agents With OpenAI Agent Development Kit
WSQ OpenAI Agents SDK courseware with 227 visual slides and 10 self-contained Python activities covering tools, RAG, orchestration, MCP, guardrails, tracing, and evaluation.
Agent Workbench
Claude Code plugins for running several coding agents at once: git guardrails, a machine-pressure gate, agent-to-agent chat, PR review and QA loops. Pick only the parts you want.
Listing Claim Check
Checks AI-written marketplace listings against the seller's item specifics before they're published: PUBLISH or REVIEW, with the exact words behind every unbacked claim. Determini…
Immune
Immune — the agent security loop that turns every attack into an antibody. MCP firewall → replayable breach trace in ClickHouse → synthesized countermeasure → replay-proven → Semg…
Voyagemesh
An intelligent multi-agent travel planning system powered by LangGraph, MCP, Guardrails, and HITL workflows
CLI
The agentic harness for AI coding agents — intelligence is rented, the harness is owned. Runs the full work cycle: intent briefs, bounded RAG context from real code intelligence,…