- Conduid
- Marketplace
- #llm-guardrails
MCP servers tagged llm-guardrails
27 live MCP servers tagged "llm-guardrails", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm-guardrails.
Agentic Security
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
Audit Tool
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pu…
Cerbia
A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, speci…
LLM Shield Proxy
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-…
Baseline
A discipline layer for Claude Code. Hooks at every tool boundary, a workflow that runs from intake to commit, and a small constitution the agent cannot bypass.
Zn Gate
Zero-trust prompt injection security gate & MCP server for AI agents (Cursor, Claude Code, Antigravity, OpenCode, Codex)
Rea
Agentic governance layer for Claude Code — policy enforcement, hook-based safety gates, audit logging, and Codex-integrated adversarial review for AI-assisted projects
Execution State Preflight
Move both the checklist and the verdict outside the model. Slot-based preconditions for irreversible tool calls — execution reads a verdict record, never a conditional.
Macos Computer Use Kit
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions ke…
Artha
Multi-agent equity research crew (Google ADK) that writes balanced briefs and refuses financial advice by construction - deterministic prompt-injection guardrail, MCP tool server,…
AI Security Platform
Control plane for enterprise AI security: inline runtime guardrails, automated red teaming with auto-remediation, AI asset posture (AI-SPM), and compliance governance. Python cont…
Guard Layer
Runtime guardrails between an AI agent and its tools: scan what it reads, gate what it does, and track the session so a secret read earlier can't be exfiltrated later. Containment…
Artha
Multi-agent equity research crew (Google ADK) that writes balanced briefs and refuses financial advice by construction - deterministic prompt-injection guardrail, MCP tool server,…
Agent Guardrails
Merge gates and safety checks for AI coding agents. Works with Claude Code, Cursor, Windsurf, Codex via MCP. Detect scope violations, missing tests, and risks before merge.
Zn
Zero-trust, bidirectional prompt injection & tool-poisoning security gate for AI agents.
Ephorate AI Governance And Monitoring
Open-source control plane for AI agent security & governance — runtime policy enforcement, tamper-evident audit, prompt-injection detection (SIEM/EDR) and compliance mapping (NIST…
Agentmoat
A security layer for AI agents: detects prompt injection, firewalls dangerous tool calls, scores inter-agent trust, and keeps a tamper-evident audit log. Works with the Anthropic…
Audit Gateway
MCP gateway: a governance and audit reverse-proxy that sits in front of any MCP server. Per-tool RBAC, multi-tenant isolation, PII redaction on tool results, tamper-evident audit…
Chaperone
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP sec…
Tulip Agents
The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can…
Lens Kit
Trainable 10-lens validation gate for AI-generated text. Outside-in: a separate model checks the output, fixed checks, inspectable findings, fail-closed. Apache-2.0 — own it and t…
Exogram SDK
Python SDK for Exogram — the execution authority layer for autonomous AI. Evaluate, permit, and audit every AI agent action.
Proven Gate
Deterministic provenance policy layer between LLM agents and their tools (including MCP) — blocks tool calls driven by untrusted data. No LLM, no network, fail-closed.
.github
Org profile and community health files for Responsible AI Labs. RAIL Score: LLM evaluation across 8 dimensions, guardrails, MCP server, red-teaming, and India DPDP / EU AI Act com…
Agent Cordon
Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.
Agent Kit
Build a runtime for Claude Code with persistence, observability, and multi-process coordination for long-running AI agents
Thelyceum 22
No description published.