- Conduid
- Marketplace
- #agent-security
MCP servers tagged agent-security
378 live MCP servers tagged "agent-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-security.
Gateway
Behavioral scoring for AI agents. Observe every action, stop what deviates, prove what happened. Observe in 5 minutes, enforce when ready.
Pluto Aguard
Security scanner and launch gate for AI agents & MCP apps — config scanning, policy coverage, risk modeling, drift detection, CI/SARIF, and launch-readiness evidence
AEGIS OS
AEGIS OS™ - Secure AI Agent Platform - 12 security layers, 5 AI backends, RBAC, TLS, MCP/A2A. Built in Rust.
Redstamp
own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, sam…
Toolpoison
Security scanner for MCP servers. Detects tool poisoning, prompt injection hidden in tool descriptions, leaked API keys, and supply-chain risk across Claude, Cursor, VS Code, Wind…
Obsign
Tamper-evident audit trail for AI agent actions. An MCP gateway that enforces signed Cedar policies, proves who delegated what, and emits evidence packs an auditor can verify offl…
Mcpradar
Security scanner for Model Context Protocol servers. Catch tool poisoning, prompt injection, and supply-chain attacks before your AI agent runs them.
Qubes MCP
Autonomous AI agents inside a Qubes-isolated sandbox - tag-scoped Admin API access with dom0-mediated trust boundary.
Mcprism
Fast single-binary security scanner for MCP (Model Context Protocol) servers — config audit, live capability enumeration, tool-poisoning detection & risk grading. Zero deps, fully…
Awesome MCP Security
A curated list of MCP security tools, frameworks, scanners, gateways, and resources.
Honeymcp
Open-source honeypot for MCP (Model Context Protocol) servers. Collects threat intel on attacks against the AI agent ecosystem.
Skillhub
Local skill registry and installer for AI agents
Starter Stack
Cloneable reference workspace for governed AI agent development — 6-layer security stack with scanner, signing, sandbox, and observability
Uncensored Fleet
Deploy a local multi-model LLM fleet (llama.cpp) with an agent harness, hermes memory, and a one-command CLI
Bounded Agent Runtime
Security runtime for AI coding agents: bounded authority, exact-candidate evidence, separate review and human gates. Works with Codex, Claude and OpenCode.
Clayseal Receipts
A signed record of what an agent asked for, what policy said, and what happened.
Patchwitness
Independent trust gate for AI coding agents: verify scope, protected CI, real checks, secrets, impact, and portable Change Passports.
Attenu Guard
In-process permission enforcement for AI-agent delegation chains: a sub-agent never holds more than its parent's authority, with an offline-verifiable audit ledger. Python + TypeS…
Ttp Protocol
See what your AI agents can cause, route them safely, and prove what happened. Open-source execution authority for AI agents — consequence preview, trust routing, signed receipts.
Assay Harness
Recipe, gate, and report layer for canonical Assay evidence artifacts: DSSE recipes, replayable digest-bound packs, CI gates.
Adtp
Cryptographic identity and delegation for AI agents — UCAN chains, RESTRICT mode (structurally impossible escalation), provably-complete cascade revocation. Single Go binary. Apac…
Limitrum
Policy kernel for autonomous AI agents.
Actiongate Jev
Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.
Invaris Agentsec
Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.
Tempus Ddb
Fail-closed B2A security gate for autonomous agent actions with signed policies and verifiable receipts.
Agent Security Guidelines
Hướng dẫn kỹ thuật an ninh cho AI Agent · Agent Security Technical Guidelines (public draft 0.1.0)
Gurdy
Runtime governance for AI agents: intercept agent-to-tool traffic, decide against a versioned Cedar policy bundle, and write a tamper-evident decision ledger a third party can ver…
Provio
A safety floor your AI agents can't get under: one policy for Claude Code, Codex, Gemini CLI, Cursor, Windsurf and MCP, judged by what each call will run, backstopped by the kerne…
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…
Mcpcustoms
MCPCustoms is the customs checkpoint for MCP tool calls: a zero-dependency TypeScript runtime semantic firewall that inspects every Massive Intelligence (IM) agent tool call befor…
AI Security Labs
Hands-on AI security labs. Build, break, understand.
Goop Shield Community
Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.
Tack Guard
Runtime risk scoring for AI agent tool calls. Catch privilege escalation, baseline deviations & exfiltration inline, under 1ms, zero deps, no LLM.
MCP
⬡ The Sato Hub MCP server — npx -y @satohub/mcp. Scored index of the onchain agent stack, Preflight, Sato Route, Agent Passports. No key, non-custodial.
Tessera
Signed provenance labels and taint-tracking policy for LLM agent security. The core library behind AgentMesh.
Guardrail
Security gateway for MCP servers — enforce tool access policies, audit AI agent activity, and detect exposed secrets.
Gate
Runtime enforcement for MCP agents: capability manifests, session taint tracking, and a non-configurable rule-of-two trifecta invariant, with a hash-chained audit log.
Vex
Agent-first red team framework for AI systems probe LLMs, agents, MCP servers, and RAG pipelines for safety failures and exploitable vulnerabilities.
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…
Pipelock Verify Python
Python verifier for Pipelock action receipts (Ed25519-signed, chain-linked)
Sentinelmcp
An automated red-teaming and reliability-auditing platform for AI agents - tests for prompt injection, tool hijacking and data exfiltration. Ships as an MCP server.
Vaerion
Open-source verification layer for AI agents — signed receipts, fail-closed policies, deterministic proof. Local-first, zero telemetry.
AI Agent
生产级 Agent Engineering 知识库与工程体系，覆盖 LangGraph、RAG、MCP、Multi-Agent、Runtime、Evaluation、Security、SRE 与 Skills。
Countersign
Your AI agent writes its own 'allow this?' dialog, so it can hide what it's really doing. Countersign draws the dialog itself, so you approve the real command, and every yes becom…
Agentic AI Security
Security analysis of MCP ecosystem – threats, defenses, benchmarks, and agent interoperability.
Breaker
Replay-verified MCP security testing and deterministic policy hardening for tool-using AI agents
Kasa MCP
KASA MCP — a permission-brokered MCP server for agent memory. Local-first, encrypted at the cell level, hash-chained audit. Research preview: we publish the attacks our own broker…
Eidolon
The cryptographic authority layer for AI agents. Watch every tool call live, delegate exactly the authority you choose, and kill it mid-session — enforced by a signed, revocable c…
Gaze
It sees the page, and it acts. Drive a real, already logged-in browser from the CLI or over MCP, with an enforceable approval gate. Chromium via CDP, Firefox via WebDriver BiDi.
Strongroom
Own your agent secrets — your agent holds a scoped, single-use lease, never the raw API key. strongroom injects the real secret only at egress, so a leaked prompt or poisoned tool…