MCP server directory
53,858 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 34,158 remote servers
- Updated every hour
MCP OpenClaw Extensionsio.github.romainsantoli-web/mcp-openclaw
138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt
Ybe Checkio.github.AddyCuber/ybe-check
Ybe Check – security and compliance orchestrator for AI-generated repositories.
EU Audit Trailio.github.jellewas/eu-audit-mcp
Tamper-evident audit trail MCP server for EU AI Act & GDPR compliance.
Guardian Enginedev.kaimeilabs/guardian-engine
Deterministic recipe verification engine — validates AI-generated recipes against master SOPs.
Cybersecurity Vulnerability Intelio.github.martc03/cybersecurity-vuln
CVE lookup via NIST NVD, CISA KEV, EPSS, and MITRE ATT&CK. 7 tools.
Environmental Complianceio.github.martc03/environmental-compliance
EPA air quality monitoring and HUD foreclosure data. 3 MCP tools for environmental and housing data.
Aguara MCPio.github.garagon/aguara-mcp
Security scanner for AI agent skills and MCP servers
Sprout MCPio.github.mepsopti/sprout-mcp
Model-tiered content pipeline — cheap models seed, expensive models verify
Bulwarkio.github.bpolania/bulwark
AI agent governance: content scanning, audit logs, policy evaluation, session management.
mcpwallio.github.behrensd/mcpwall
iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.
Gibs MCPgithub.com/buildsyncinc/gibs-mcp
Regulatory compliance for the AI Act, GDPR and DORA, with article-level citations.
FedRAMP 20x Requirementsio.github.KevinRabun/FedRAMP20xMCP
An MCP server that provides access to FedRAMP 20x security requirements and controls.
Conan MCPgithub.com/conan-io/conan-mcp
Conan C/C++ package manager: create projects, manage dependencies, check licenses and scan for security vulnerabilities.
GDPR Shift-Left Complianceio.github.KevinRabun/GDPRShiftLeftMCP
GDPR compliance MCP server - article lookup, DPIA, ROPA, DSR, IaC analysis, Bicep templates.
Primordiagithub.com/oerc-s/primordia
Economic settlement for AI agents: receipt verification, metering, net settlements, credit lines and balance sheets.
Chrome MCP Securegithub.com/Pantheon-Security/chrome-mcp-secure
Security-hardened Chrome automation and logins with post-quantum encryption, a credential vault, memory scrubbing and audit logging.
Secretctlgithub.com/forest6511/secretctl
Secrets manager that injects credentials into commands as environment variables so agents never see plaintext secrets, and sanitizes command output.
Microsoft Sentinel Data Explorationcom.microsoft/sentinel-data-exploration
Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de
Bright Securitycom.brightsec/mcp
Enables AI agents to access Bright Security tools for app discovery and security testing.
MCP Server Wazuhgithub.com/gbrigandi/mcp-server-wazuh
Access real-time security alerts and event data from Wazuh SIEM.
Blind Auditorgithub.com/Sim-xia/Blind-Auditor
Make AI self-correct its generated output through prompt injection, independent self-auditing and context isolation.
MCP Server Thehivegithub.com/gbrigandi/mcp-server-thehive
TheHive integration for collaborative security incident response and case management.
MCP Server Cortexgithub.com/gbrigandi/mcp-server-cortex
Cortex integration for observable analysis and automated security responses.
MCPower Security Proxyio.github.MCPower-Security/mcpower-proxy
Security proxy that automatically wraps MCP servers with real-time monitoring and policy enforcement
MCPower Security Proxyio.github.ai-mcpower/mcpower-proxy
Security proxy that wraps MCP servers with real-time monitoring and policy enforcement
Firebase MCPgithub.com/gannonh/firebase-mcp
Firebase services including Auth, Firestore and Storage.
AIM MCPgithub.com/AIM-Intelligence/AIM-MCP
Security-focused safety guidelines and content analysis for AI agents.
Secops MCPgithub.com/securityfortech/secops-mcp
Security testing toolbox that combines open source tools behind a single interface for pentesting, bug bounty hunting and threat hunting.
Screenygithub.com/rohanrav/screeny
Privacy-first macOS MCP server that provides visual context for AI agents through window screenshots
CLI MCP Servergithub.com/MladenSU/cli-mcp-server
Command-line execution with customizable security policies.
BloodHound-MCPgithub.com/MorDavid/BloodHound-MCP-AI
integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language que...
MCP AI SOC Shergithub.com/akramIOT/MCP_AI_SOC_Sher
Dynamic SOC security threat analysis for a Text2SQL AI agent.
MCP Recongithub.com/nickpending/mcp-recon
Conversational recon with httpx and asnmap: domain analysis, security header inspection, certificate analysis and ASN lookups at multiple recon levels.
MCP Securitygithub.com/fr0gger/MCP_Security
Query the ORKL API to fetch threat reports, analyze threat actors and retrieve intelligence sources.
HALgithub.com/dean/HAL
HTTP toolkit providing all 7 HTTP methods (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) with secret substitution, comprehensive error handling, and support ...
Nobulexgithub.com/arian-gogani/nobulex
Proof-of-behavior enforcement for AI agents: define permit/forbid/require rules, enforce them at runtime and keep hash-chained, tamper-evident audit logs.
io.github.atharv-santosh/tracerlabio.github.atharv-santosh/tracerlab
Build and verify Cisco Packet Tracer networks from an AI agent.
BlueNexus Universal MCPai.bluenexus/universal-mcp
Connect your AI to all your data - 200+ sources, intelligently filtered, compliance-ready.
io.github.The-Pixel-Boys/shield-kyaio.github.The-Pixel-Boys/shield-kya
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
io.github.99blakeD99/the-metis-fca-handbook-ai-harness-mcpio.github.99blakeD99/the-metis-fca-handbook-ai-harness-mcp
MCP server for FCA Handbook compliance analysis with verbatim citations.
io.github.crosstabs/crosstabsio.github.crosstabs/crosstabs
Local survey workflow and statistical crosstab analysis with auditable evidence
io.github.GuardBee/reverse-shieldio.github.GuardBee/reverse-shield
Audits shipped apps for how easily they can be reverse engineered
ai.greyridgesignals/tech-riskai.greyridgesignals/tech-risk
Free MCP security scan: tool-poisoning & prompt-injection audit (OWASP LLM01/08) + trust badge
io.github.mrfentmen/totp-mcpio.github.mrfentmen/totp-mcp
Generate and verify TOTP codes offline: RFC 6238 with SHA-1/256/512 and fresh base32 secrets
io.github.mrfentmen/http-check-mcpio.github.mrfentmen/http-check-mcp
Check a URL live: status, timing, redirect chains and security headers; private hosts blocked
io.github.qso-graph/hamqth-mcpio.github.qso-graph/hamqth-mcp
HamQTH.com MCP server. Free callsign lookup, DX spots, RBN data, SAVP verification.
io.github.qso-graph/eqsl-mcpio.github.qso-graph/eqsl-mcp
eQSL.cc MCP server. Inbox download, QSO verification, Authenticity Guaranteed status.
io.github.Gowthaman90/mcp-bastionio.github.Gowthaman90/mcp-bastion
Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data. Last synced Oct 29, 2026.
Frequently asked questions
What is MCP?
The Model Context Protocol is an open standard that lets an AI assistant (Claude, ChatGPT, Cursor, an agent) call outside tools and read outside data through a "server". A remote server is a URL you add to your client; a local one runs on your computer from a package (npm, PyPI, Docker).
How do I add an MCP server to Claude or Cursor?
Open the server's page here and copy its configuration block into your client's MCP settings file, then restart the client. Remote servers need only the URL; local ones need Node (npx), Python (uvx) or Docker installed.
Are these servers safe?
Anyone can publish to the registry. A server can read what you give it access to and act on your behalf, so prefer servers with public source code from a publisher you recognise, and grant the smallest scope that works.