- 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.
Trustline MCP
Zero-trust policy engine for MCP tool calls with deny-overrides rules, redaction, quotas, and tamper-evident audit logs.
Vulnerability Detection
Self-contained MCP security server that scores AI agent tool-calls with a rule-based library + behavioral detector, giving explainable, MITRE-mapped verdicts for known attacks
Apm Demo App 003
APM Security Demo App 003 — ASP.NET with MCP configuration violations
Agentlock
An MCP server wrapper that gates tool calls on where a value came from, not what it says. Catches cross-hop prompt-injection laundering.
Agentx MCP
Keyless MCP security shield: wrap any MCP server so a poisoned tool call cannot wreck your system and your agent keeps working. Launcher for agentx-security-sdk.
Detonator
Dynamic exploitability testing for AI agents and the MCP servers they use
Agentsmith
Config-first scaffolding and orchestration for multi-agent workflows
Belay MCP
Transaction firewall for AI agents. Preview, govern, verify and rewind MCP and native tool calls with deterministic policies, human approvals and signed evidence.
Delegated Authority Webmcp
WebMCP operations console where a human delegates a bounded envelope of authority and the browser's registered tool surface is what enforces it. Revoke a capability and the tool s…
Heron MCP
Free, signed 0-100 trust scores for what an AI agent runs: skills, MCP servers, and the agent itself. Public methodology, wallet-signed (EIP-191).
Prompt Injection Lab
Hands-on prompt injection lab with live attack demos for agent, MCP, and memory poisoning training.
Identitykit
Portable, signed, resolvable agent identity plus the cross-walk onto DID, FIDO, AP2, and EUDI. Deterministic, fail-closed.
Agent Security Bench
Open bench for AI coding-agent ML eval + agent security (prompt injection, jailbreak, tool overreach) with machine-readable receipts
Agent Sbom
Capability-aware SBOM and SARIF scanner for agent skills, MCP manifests, prompts, and scripts.
Toolguard
Runtime allowlist and policy for agent tool-calls
Toolproof
Trust grades, capability lockfiles, and signed evidence for the AI tool supply chain. Scan any MCP server or API before your agent connects. Paid by nobody we scan.
Security Readiness Guide
Security checklist, threat model, and production readiness standard for Model Context Protocol (MCP) servers.
Jak Shield
Secure AI agent tool calls by blocking destructive actions, redacting sensitive data, and enforcing human oversight with this universal security gateway.
Trifecta Guard
Runtime security middleware that blocks lethal prompt-injection capability chains in AI agents.
Axguard
Adversarial security testing for AI agents — MCP, A2A, x402/L402, and live tool-use. Tests as YAML, evidence as JSON.
Agent Permit Office
Pre-flight security checks for AI coding agents before tools, secrets, memory, MCP, or CI write access.
Project Door
Proof that a verified human is accountable for what an AI agent does. Open protocol for human attribution on MCP connections.
Codex Tripwire
Live audit and observability for Codex CLI - commands, network policy decisions, MCP calls, and Web Search activity.
Holdcall
The control that stays on your machine: a local relay that decides every MCP tool call, holds the dangerous ones for a human, and keeps a record you can verify offline.
Threat Detection Lab
Agent exposure review ("what changes if I add this tool to my agent?"), a deterministic detection-boundary harness, and a CTI pipeline. Public data only; every figure measured.
Drift Check
Zero-execution MCP security preflight + GitHub Action. Detect mutable package references before AI agents run them. Try any public repo in the browser.
Damn Vulnerable Agent Asset Corpus
Damn Vulnerable Agent Asset Corpus: benchmark fixtures for agent-asset scanners and AAC release assurance.
Trust Scoreboard
Open-source MCP security dashboard and trust scoreboard for Model Context Protocol servers, AI agents, tools, permissions, identity, provenance and risk.
Flint Agentgate
Identity, semantic authority, tool assurance, and policy-enforced WebMCP for AI agents
Capability Delta Receipts
Deterministic capability delta receipts: hash-linked JSONL receipts for agent research trajectories with a fail-closed envelope boundary
Aeromesh
Declarative, signed, sandboxed standard for AI agents & workflows (DAM v0.1 + DWM v0.1), compiled into LangChain Deep Agents
Jovanipink Adk
Secure Google ADK runtime infrastructure for reviewed, non-executable Agent Skill bundles.
Eczid Agent Trust
Official ECZ-ID Agent Trust product and documentation hub. Local-first agent inventory, authority and change inspection for VS Code.
Whaleguard Redlab
Local-first, scope-guarded AI red-team lab for authorized LLM, Agent and MCP security evaluation.
Llmsafe
Static security scanner for Python AI agents, LLM apps, and MCP servers.
Cutout
Offensive framework for authorized security testing of agentic AI systems — recon, exploit, persist, and pivot across MCP servers and agent chains.
Divergence
Precision-first security analyzer for MCP servers and agent skills. 0% false positives on traps, 96% recall.
Codelytra
Open-source, local-first AI security scanner for JavaScript and TypeScript LLM, agent, RAG, tool-calling, and MCP applications.
Agent Trust Plane
Authorization and security regression testing for AI agents and MCP tools.
Simdiff
The effect layer for AI-agent firewalls — simulate an action, get a canonical effect delta. Zero-dep, deterministic, fail-closed. 5 domains (fs, sql, shell, http, solana).
Svr Verify
Signed Verification Receipts for deterministic AI verification: CPU-only, Ed25519-signed, reproducible, independently verifiable.
Reachable Agent Plugin Installer
Claude Code marketplace for the REACHABLE plugin (generated from the signed adapter). Not the scanner.
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.
Agentomy Agent
Free-forever governance peer for AI agents. Score, flag, and audit any agent session in 30 seconds, no infrastructure. Open (MIT) system prompt plus TypeScript/Python SDK. Part of…
Agentinbox
Ask-gate consumer (Slack/terminal/CI/mobile)
Agentpolicy
Cedar policy decision point: allow / deny / ask / rate-limit / redact
Avalix AI
Avalix (avalix.ai, est. 2026) is a custom AI implementation team — "three cyber engineers and one CTO" — that audits small and mid-size businesses for time and revenue leaks and b…
Verus
Security infrastructure that converts untrusted financial content into verified, signed context for trading agents.
Agent Risk Linter
Offline-first security linter for Agent Skills, MCP configs, scripts, and CI workflows.
Linklint
Read-only mirror of gitlab.com/bart-turczynski/linklint (issues and development there). An explainable, offline-first, agent-native URL inspector — detects deceptive URLs and tell…