security
180 servers · 12,680★ total
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS scoring, CISA KEV, MITRE ATT&CK, Shodan, VirusTotal, and more.
Consequence firewall for machine actions. EMILIA Gate verifies exact authority before money, code, permissions, infrastructure, or regulated state changes; the open protocol makes the evidence independently verifiable.
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
66-tool MCP server for dark web intelligence — breach data, ransomware tracking, Tor .onion access, malware analysis, blockchain intel, exploit search, stealer logs
120-tool MCP server for real-time global intelligence: markets, SEC filings, conflict, military, cyber, climate, news, and 30+ domains. AI situation briefs that cite their sources, user-defined geofences with escalation scoring, cited daily digests, live SSE dashboard. MIT, no paid API keys.
Production-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability management, compliance (PCI DSS, GDPR, HIPAA, NIST CSF, ISO 27001) and active response. Connect Claude or any LLM to your SOC. OAuth 2.1, RBAC, multi-cluster, air-gap ready.
A secure local gateway for AI agents to reliably call approved enterprise APIs, tools, and services.
Secure MCP server for whitelisted shell command execution with stdin, argv pipelines, timeouts, and structured audit logging.
CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Works with Claude Code, Codex, Gemini CLI, and Claude Desktop.
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.
MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship analysis, and pagination support.
MCP Armor continuously secures and monitors Model Context Protocol operations through static and dynamic scans, revealing hidden risks in agent-to-tool communications.
Reticle intercepts, visualizes, and profiles JSON-RPC traffic between your LLM and MCP servers in real-time, with zero latency overhead. Stop debugging blind. Start seeing everything.
A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com
MCP server for Slither static analysis of Solidity smart contracts
Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.
A powerful MCP (Model Context Protocol) Server that audits npm package dependencies for security vulnerabilities. Built with remote npm registry integration for real-time security checks.
AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.
OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.
Collaborative application security testing between humans and agents via CLI and MCP
Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.
MCP security testing framework for evaluating Model Context Protocol server vulnerabilities
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.
MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF, and HTML output. For authors and platform teams; CI-ready, no cloud API.
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wraps any MCP, 20 included (Postgres, MySQL, MongoDB, GitHub, Stripe, Snowflake, etc.). 84% fewer tokens, ~3x faster, holds PII leaks. AGPL or commercial.
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server (rami-kali) for controlled, extensible offensive and defensive workflows
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.
Security scores for 800+ MCP servers. 9 analyzers scan for prompt injection, toxic flows, and attack surface risks. Updated daily. 🛡️
🔐 50+ MCP Security Servers for AI-Powered Pentesting | Integrate Nmap, Burp Suite, Nuclei, Shodan, BloodHound, Semgrep, Trivy | Model Context Protocol for Cybersecurity
Discover, govern and control access to MCP servers and agent skills across your organization
Offensive MCP server auditor: detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.
Demo agents showcasing CapiscIO Agent Guard and MCP Guard — trust badges, identity verification, and tool-level authorization for A2A and MCP protocols
MCP is being adopted rapidly. Security guidance is lagging behind. This checklist gives security engineers, platform teams, and technical leaders a clear, actionable baseline for securing MCP deployments , whether you're shipping an internal tool or a customer-facing AI agent.
Deterministic CI scanner and surface-risk scoring for MCP (Model Context Protocol) servers.
Shodan MCP server for Claude, Cursor & VS Code. 20 tools for passive reconnaissance, CVE/CPE intelligence, DNS analysis, and device search. 4 tools work free without an API key. OSINT and vulnerability research from your IDE.
Reference MCP App for Elastic Security — interactive SOC dashboards inside Claude, Cursor, and other MCP hosts.
23-tool MCP server for CVE & vulnerability intelligence. NVD, EPSS, CISA KEV, GitHub Advisory, OSV — unified in one server. Risk scoring, bulk triage, exploit search. 2 dependencies, runs with npx.
Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.
Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.
MCP server that gives LLM agents read-only shell access over SSH. Powers Fawdy (fawdy.com)
A trustless MCP server that replaces the generic shell tool with validated, sandboxed, purpose-built execution tools for AI coding agents.
Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.
AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.
Heddle — The policy-and-trust layer for MCP tool servers. Turn YAML configs into validated, policy-enforced MCP tools.
Optimized, auditable execution for Codex and Claude Code: bounded repository context, verified patches, and reproducible paired benchmarks.
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
🐜 AI-native modular coding workspace — 127 modules, 424 MCP tools, 21K+ zero-mock tests, multi-agent orchestration (Claude/Gemini/GPT), PAI integration
The Open-Source MCP Firewall & Security Gateway for AI Agents. Inspect, redact, and control tool calls. Proxy mode (universal) and Inline SDK mode (Go).
Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.
🚀 Discover and explore a curated list of MCP servers, tools, and resources for AI assistants, enhancing your development and productivity.
Vibe code fast. Ship like an engineer. AI engineering framework packaged as an MCP server that enforces TDD, security scanning, pentesting, secret management, QA audits, and deployment to a securely configured VPS — automated with up to 100× fewer exploration tokens.
Local CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.
🚀 Ultimate Developer Productivity Suite - 11 specialized MCP servers for AI-powered code analysis, security scanning, browser automation, and workflow orchestration. FastAPI + React + TypeScript + Docker ready.
A production-ready Model Context Protocol (MCP) server for Idira (formerly CyberArk) Privilege Cloud integration. Enables AI assistants and MCP clients to securely interact with privileged account management, safe operations, and platform configurations.
Zero-auth, security-hardened cross-domain research MCP server: web, academic, GitHub, news, weather, macro/finance, SEC, biomedical, Bluesky, YouTube. SSRF and prompt-injection defenses.
Security scanner for Model Context Protocol (MCP) with capability graph analysis. Detects emergent attack chains across multi-server AI agent deployments that no individual tool scan can find.
VytalLink is a digital health platform connecting personal health data—including Apple Health, Google Fit, and wearables—with AI assistants like ChatGPT and Claude. Includes a Flutter app, Node.js MCP server, and Firebase landing page. Focused on privacy and user control.
Smart contract security auditor for Claude Code — vuln detection, exploit PoCs, mainnet-fork simulation, audit cards, on-chain certificates. Solidity + Vyper · 38 commands · 19 agents · 33 skills · 9 MCP servers.
Stop storing API keys in mcp.json and shell profiles. kprun solves this by keeping secrets in an encrypted KeePass vault and injecting them only into spawned processes. Designed for MCP servers, coding agents, and dev scripts. Features: per-proces injection, audit logging, cross-platform, KeePassXC-compatible, CI/CD-ready.
Open-source, self-hosted Zero Trust policy enforcement layer for MCP servers.
10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
A security-first bridge between Claude Code (MCP) and Chrome — HMAC pairing, domain allowlist, per-domain evaluate opt-in.
OAuth 2.1 and enterprise SSO for remote MCP servers without API keys in client configs.
Open source control-plane proxy for AI agents: identity, policy, budget, audit for MCP and beyond
MCP server for secure SSH remote management — 337 tools across 74 groups for DevOps, Docker, Kubernetes, databases, systemd, Windows, cloud, compliance & more. Built in Rust.
MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.
🚀 The first and only Model Context Protocol (MCP) server for 20i web hosting services. Transform your hosting management with AI-powered automation through Claude, ChatGPT, and other AI assistants. 76 tools | 28.0% API coverage
Auth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
Use ChatGPT as the brain and your local computer as the hands — a safe, permissioned local MCP gateway with default-deny security, local approvals, and full audit logging.
MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.
Production-ready MCP server for Tenable Security Center with intelligent caching. 90% token savings, 1000x faster responses.
MCP server exposing WordPress internals to AI - hooks, schema, security, and test data. Inspired by Laravel Boost.
The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
MCP server for unified threat intelligence - AlienVault OTX, AbuseIPDB, GreyNoise, and abuse.ch feeds
Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.
The open standard for cryptographic identity and trust verification of autonomous AI agents.
Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.
Give ChatGPT fast, safe, and auditable visibility into your VPS through MCP.
Agent Identity Protocol -- verifiable, delegable identity for AI agents across MCP and A2A. IETF Internet-Draft. PyPI: agent-identity-protocol
🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 52 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard
An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.
MCP tools for semantic search in github/advisory-database
A cross-platform Codex setup kit with specialist agents, curated skills, safe MCP defaults, preview-first installation, and clear verification.
Security for AI agents & MCP — map how MCP servers, skills, and memory chain into exposure paths. Toxic-flow detection, cross-surface graph, drift & policy-as-code. Local-only, no telemetry.
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires human approval for risky actions
A fast, OS-sandboxed Model Context Protocol gateway with an embedded Code Mode engine and shell-output token compression, in a single Rust binary.
MCP-native secret scanner in one fast Rust binary: engine, CLI, and MCP server. Finds API keys and secrets, skips known-public fixtures, verifies live keys with a real provider call, and applies env-var rewrites. Privacy invariant: the raw secret never leaves disk.
MCP server for Sliver C2 - Adversary emulation framework integration for AI assistants
Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.
Tamper-evident audit log for Go: an append-only, hash-chained, optionally Ed25519-signed log/slog handler, with offline logx verify. Built on the standard library, zero third-party dependencies. Also a full slog toolkit (colored output, JSON, rotation, fan-out, CLI).
Enterprise and government control plane for AI agents and MCP servers: govern, secure, observe, and audit. Rust, multi-provider (incl. major Chinese models).
A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.
AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.
104-tool DNS Security Intelligence MCP Server — DNSSEC, hijacking, tunneling, typosquatting, email security, CT monitoring, blocklist, infrastructure audit. 100% local, zero API keys required.
Comprehensive security scanner for MCP (Model Context Protocol) servers. 12+ analyzers, 117 YARA rules, ML-powered threat detection, dual scoring system. Detects prompt injection, tool poisoning and more
A security-first MCP server for pfSense — READ-only today by design; WRITE is staged behind explicit safety architecture, not a feature flag.
Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.
AI-driven DFIR framework: an MCP server that turns Claude Code into an autonomous digital-forensics analyst on SANS SIFT - correlates disk + memory evidence, enforces a deterministic evidence-provenance gate, and produces auditable, hash-chained investigation reports.
Hardened Model Context Protocol (MCP) server for pCloud, in Go. Path-traversal-proof downloads, OAuth-only auth, single static binary.
A PostgreSQL MCP server that automatically detects and redacts PII in query results before they reach AI agents.
Cryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.
A local-first permission firewall and approval layer for AI agent tool calls.
MCP server that gives AI agents a local security scanner before they install or trust third-party tools.
The agent-native Supabase killer: SQLite speed today, distributed cloud next, without the PostgreSQL tax.
Open-source zero-trust proxy for MCP servers — adds OAuth 2.1, tool-level RBAC, audit logging, and rate limiting to any MCP server. One Docker command, zero code changes.
Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift
EnigmAgent — 6-layer encrypted vault for AI agents (AES-256 + ChaCha20 + Blowfish + Fernet + 3DES + RSA). P2P sync via Gun.js. Zero cloud. Part of P2PCLAW.
Security scanner and install and runtime protection suite for Model Context Protocol (MCP) servers
Universal MCP server: connect any OpenAPI/Swagger, GraphQL, gRPC or SOAP API to AI agents. Security-first, local, token-efficient. Any API. One server.
🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
Canonical unified MCP server in golang for Hugo sites — oauth register and self registered token
SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.
Security-first MCP server for Odoo 17/18/19 — YAML-driven security, zero Odoo-side code, 27 tools + 5 resources + 7 prompts
Mobile app security analysis MCP server for Android APK and iOS IPA files
MCP server — read-only log access for AI assistants. Debug your Linux server with AI, without giving the AI shell access.
Open Agent Security Fabric — red-team agentic AI, MCP firewall SDK, action oracles & SARIF CI gates. Assure, Enforce & Govern. Python + TypeScript. OWASP LLM/Agentic/MCP Top 10.
Turn your ChatGPT conversations into safe, auditable local execution. PatchWarden lets you discuss ideas and plans with ChatGPT, then hand the approved plan to local AI agents for guarded, traceable implementation—with scoped permissions, independent verification, and a complete execution record.Turn your ChatGPT conversations into safe, auditable
MCP server for Microsoft Patch Tuesday - query MSRC security updates, CVEs, and KBs with EPSS + CISA KEV enrichment. No API keys. Works with Claude, Copilot, Cursor, and any MCP client.
Universal cyber assistant: ~80 audited Kali tools + an expert skills library, driven by any model over MCP or direct run
The guardian layer for AI agents — identity, secrets, audit via MCP. Gate + Vault + Watch.
Intercept & tamper proxy for MCP traffic — X-ray and rewrite the JSON-RPC between an AI agent and its MCP servers. Burp Suite for AI agents. Authorized testing only.
Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.
Sandbox any MCP server in one line. Firecracker microVM isolation for Claude Desktop, Cursor, Windsurf, and every MCP client.
Zero-trust security sidecar for AI agents - MIT, single Go binary, <5ms p99 overhead, protects Claude Code/Cursor/Codex/Gemini CLI/Windsurf
Cage untrusted MCP servers in containers, compose them into agents, and share them over any OCI registry. Signed, sandboxed, no Docker required.
Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification
Command-line interface for Declaw — security-first sandboxing for AI agents
Universal digital fingerprinting MCP server — 103 techniques in 13 tools for TCP/TLS/SSH/HTTP/DNS/WAF/IoT fingerprinting, C2 detection, OSINT enrichment
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.
Autonomous AI agents inside a Qubes-isolated sandbox - tag-scoped Admin API access with dom0-mediated trust boundary.
Day-zero supply-chain checker for npm + PyPI, as a local MCP server for AI coding agents. Calls check_package before installs to surface contextual anomalies.
128-tool MCP server for steganography analysis — LSB detection, chi-square steganalysis, RS analysis, JPEG/F5/JSteg/OutGuess detection, BPCS, video & GIF stego, network covert channels, MP3 stego, spread spectrum, archive stego, QR code analysis, audio stego, text encoding, file forensics. 100% offline, zero API keys.
One-command setup for a full VS Code Copilot Chat agent-skills stack on Windows - 144 skills, 18 CLIs, 11 MCP servers, 39 fork mirrors, and a 74-site design-system library, all security-gated.
Find the MCP schema issues eating your context window. 156 checks. Grade A+ through F. ESLint for MCP.
Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.
Security proxy for MCP servers. Catches indirect prompt injection attempts before they reach your AI agent.
🔍 Enable AI-driven network security scanning with a production-ready Nmap MCP server supporting diverse tools, scan types, and timing templates.
MCP server that gives AI assistants access to a Kali Linux Docker environment for security testing
MCP server that runs sudo via a native OS password dialog so the password never enters the model context.
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
Self-hosted MCP gateway: AI agents get audited, SSO-gated, read-only database access without ever holding a DB credential.
Security linter for environment variables, Docker, CI, Kubernetes, and runtime configuration.
Model Context Protocol (MCP) server that enables Claude to perform comprehensive security audits on Solidity smart contracts using Slither, Aderyn, and built-in pattern detection
MCP server for NowSecure Platform: pull remediation findings and generate clean PDF reports, bypassing the broken UI report renderer.
Diagnose, secure, and benchmark your MCP servers. Zero-config CLI for Claude Code, Cursor, VS Code, and Windsurf.
Local safety-gated MCP bridge for AI agents and Outlook mail & calendar: metadata-first reads, explicit content, reviewed sends, guarded cleanup.
A Roslyn analyzer that catches prompt-injection and tool-poisoning in C# Model Context Protocol (MCP) server tool descriptions at build time. MCPGxxx diagnostics, code fixes, and a CI gate.
Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.
Your SIEM answers live behind a console you babysit. wazuh-mcp reads Wazuh alerts, agents, and CVEs straight into your AI client. Read-only, nothing leaves the box.
90-tool MCP server for software supply chain security — OSV, GHSA, NVD, EPSS, CISA KEV, npm, PyPI, crates.io, RubyGems, NuGet, Packagist, Go, deps.dev, Scorecard, Rekor, ClearlyDefined, Repology, typosquatting detection
MCP server for AI security intelligence. Check any MCP server for supply-chain threats before installing -- from Claude, Cursor, or Windsurf.