- 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.
Engineerious.com
Agent-security tracking for engineers running AI in production. Next.js 15 + Postgres, with a Zod-enforced provenance schema that makes 'verified' impossible without a named human…
Haechi
Experimental self-hosted AI context enforcement layer for LLM, MCP, vLLM, Ollama, and agent traffic.
Maxion MCP
In-process security gate, prompt injection defense, and autonomous thermal governor for MCP AI agents.
Tool Sanitizer
Detect and neutralize Unicode concealment codepoints in MCP tool metadata (covert-channel control). AGPL-3.0-or-later.
Delicti
Corpus delicti for AI agents — mandate before act, effector receipts, Flare FDC as second witness, bonded consequence. Live on Coston2.
Mylonite
Open-source AI-layer security testing — probes your AI agent for weaknesses and writes a validated regression test for each one it finds, gating CI.
Agent Skill Scan Action
GitHub Action: Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition r…
Attenu Guard Ts
Attenu Guard for TypeScript — per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verified…
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.
Pod
pod — least-privilege compiler for AI agents. Compile a least-privilege policy from what your agent actually did, then prove what happened.
Mcpbait
Red teaming framework that proves whether an MCP-speaking agent can be hijacked by a malicious server
Mandatum
Verifiable delegation for AI agents — signed chains rooted in a human sponsor, attenuating at every hop, revocable per link, and evaluated across whole action sequences.
Trustdex
Trust policy layer for AI agents, MCP servers, skills, and plugins.
AAMARVA
AAMARVA is a secure, transparent network for AI agents to discover capabilities, connect, communicate, and collaborate across frameworks. It prioritizes private agent communicatio…
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.
Agent Governance
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Delegation Chain Spec
ADCS: open spec for agent-to-agent delegation chains — scope intersection, budget propagation, cycle prevention, audit.
Cunning Claw
Y dyn hysbys — a local-first AI butler that owns the glass and the hands. Sees your screen, runs your shell, speaks at dawn in Welsh, and asks a human before consequences. Built i…
Watchlight De
Watchlight Developer Edition for Agent Runtime Governance - AI Security - AI Agent Security
Checkrd SDK
Policy enforcement, kill switch, and signed telemetry for AI agent API calls. Python + JavaScript SDKs with a WASM-sandboxed policy engine.
Arcjet Go
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Go cod…
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.
Agent Authority Check
FOXIFY deterministic authority preflight for MCP servers and AI agents: bind authority, inspect consequence, preserve evidence.
Openclaw Nie Guard
Cryptographic trust mediation layer for AI agent frameworks. Apache 2.0 reference architecture composing device-attested admission, short-TTL scoped capabilities, runtime continui…
Maxwells Defense
Adaptive proof-of-work defense for AI agents. Asymmetric thermodynamic cost: attackers dissipate, defenders verify in O(1). Reference implementation of T-IB-09 (Adversarial Dissip…
Truecopy Action
Gate every agent skill & MCP server change in CI — the GitHub Action for truecopy, the supply-chain gate for AI agents. Verify truecopy.lock for drift & poisoning, or poison-scan…
AI Plan
Review capability drift in AI agent skills, plugins, and MCP configurations.
Agent Trust Broker
IANUA Agent Trust Broker (ATB): identity issuance and Zero-Trust policy enforcement for AI agent fleets — short-lived scoped identities, per-action allow/deny/escalate, hash-chain…
Smallprint Tools
Small Print's open tools: the disclosure lab, and soon the command, the MCP server and the plugin
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…
Safetripwire
MCP SafeTripwire · MCP 安全绊线。Windows MCP security broker: tool-poisoning checks, manifest integrity, behavior baselines, blacklists, blocking and audit logs. By luke0485. Preview;…
Axiru Gate
One payment gate for every agent platform. Deterministic allow, hold, or deny before money moves, with a receipt. Adapters for Paperclip, AgentCore, Grok Bot, NVIDIA OpenShell, an…
Agent Passport
Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI an…
Prism
Local MCP gateway in your system tray. Connect Claude Code, Cursor, and Codex to one endpoint, aggregate your MCP servers, and approve or deny tool calls with human-in-the-loop po…
Firewall
Runtime security proxy for the Model Context Protocol (MCP). The Cloudflare WAF for AI agents. Powered by ClawGuard.
Gateway
Local-first firewall and black-box run reporter for MCP tool calls: block poisoned tools, detect drift, rate-limit agents, and audit runs.
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…
Cap
What can this MCP server actually do — and has it changed since you trusted it? Inspect its declared capabilities, seal them in a lock file, and get told when a later version can…
Breaker
Replay-verified MCP security testing and deterministic policy hardening for tool-using AI agents
Knostic
Knostic — independent third-party profile of a public API surface, by API Evangelist. Knostic secures the AI agent supply chain inside the enterprise. Its platform discovers shado…
Elodea
Inline policy enforcement proxy for AI agents: OPA policies on MCP tool calls, human approval for risky actions, and a hash-chained audit ledger.
Agentic AI Security
Security analysis of MCP ecosystem – threats, defenses, benchmarks, and agent interoperability.
Agent Mandate
Task-bound authorization for AI agents: exact approvals, atomic limits, credential isolation, and execution receipts.
Awesome Agent Supply Chain Security
A curated list of tools, research, standards and datasets for the security of AI agent extensions — skills, MCP servers, plugins and rules files.
Invaris Labs Website
Website for Invaris Labs: security infrastructure for autonomous AI agents. Presents AgentSec (adversarial security testing) and AgentAuth (agent identity and delegated authorizat…
EMO Cyber Agent
The security subagent your AI stack can trust: scoped read-only audits, evidence-backed findings, 7 MCP tools. 2738 tests green.
Two Key
Authorization and execution control for AI agents — independent policy and judge approval before consequential tool actions execute. MCP gateway, capability tokens, auditability,…
Recon
Reverse-engineer any MCP server's tool surface in 30s. Companion to capnagent.
Trust
Preflight security scanner for MCP servers — map capabilities, scan install command, code, dependencies & metadata, and get an evidence-based APPROVE/BLOCK decision. CLI + GitHub…
Guard
Adversarial fuzzer for MCP servers — dynamically break Model Context Protocol endpoints. Shell injection, SSRF, overflow, type confusion, prompt injection probes. Zero-dep Python…