MCP server directory
53,911 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 34,198 remote servers
- Updated every hour
io.github.dockndevai/mcp-androidio.github.dockndevai/mcp-android
Control Android devices over ADB from AI agents — safe-by-default, read-only by default, audited.
com.screenata/compliancecom.screenata/compliance
Manage compliance controls, policies, and audit readiness for SOC 2, HIPAA, ISO 27001 and more.
io.github.w0h1v/virustotalio.github.w0h1v/virustotal
MCP server for querying VirusTotal API with comprehensive security analysis tools.
io.github.matematicsolutions/mcp-eu-complianceio.github.matematicsolutions/mcp-eu-compliance
Offline MCP server: EU digital/data/cyber compliance full text (14 regs), verbatim + citations.
co.auditro/auditroco.auditro/auditro
UAE ICV compliance: governed scores, evidence gaps and actions with deterministic numbers.
io.github.atef-ataya/depwireio.github.atef-ataya/depwire
Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination
io.github.nagameTW/mcp-server-malcolmio.github.nagameTW/mcp-server-malcolm
MCP server for Malcolm (Zeek/Suricata/Arkime/OpenSearch): threat-hunting access for AI agents
io.github.ark-forge/prove-itio.github.ark-forge/prove-it
Free public benchmark for AI agents: compliance tasks, every claim checked against signed receipts
overflo.wsws.overflo/overflows
Look up CVEs, CISA KEV, EPSS and open-source package vulnerabilities, including malicious packages.
io.github.lemonaide152/meldio.github.lemonaide152/meld
Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets.
io.github.x-tkn/x-tkn-mcpio.github.x-tkn/x-tkn-mcp
Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back.
io.github.f-tiger/agiscorecard-web3-proofio.github.f-tiger/agiscorecard-web3-proof
Estimate zkML proving and verification costs and latency from supplied measurements; no proofs run.
io.github.sukrutkrdg/warden402-mcpio.github.sukrutkrdg/warden402-mcp
Pre-execution security for AI agents on Base: guard token/tx/address + per-agent spend firewall.
com.santosautomation/site-auditcom.santosautomation/site-audit
Website intelligence audits for AI agents: free preview plus x402-paid Agent Readiness scoring
ca.arrowmem/arrowmem-mcpca.arrowmem/arrowmem-mcp
Free Ollama hardening checker, plus tools for privacy architecture and the Data Dignity Standard.
co.encorehq/encoreco.encorehq/encore
Create, refine, and visually verify work across the Encore studio.
io.github.marcelinero/auditoria-skillsio.github.marcelinero/auditoria-skills
20 SKILLs de auditoría interna para agentes de IA según IIA, COSO, NIST, ISO, COBIT y ACFE.
io.github.forgemeshlabs/aso-audit-mcpio.github.forgemeshlabs/aso-audit-mcp
ASO Scanner — the free Agent Readiness scanner as an MCP server. Measures your ASO Score (Agent.
io.github.forgemeshlabs/coinopai-mcpio.github.forgemeshlabs/coinopai-mcp
Auditable market intelligence with calibrated forecast ranges, anomaly review, outcome.
com.vulnrable/vulnrablecom.vulnrable/vulnrable
Security grades for MCP servers and npm/PyPI packages, ranked by CISA KEV and EPSS.
dev.workers.sebastiaan-ba3.mcpgateway/toolsdev.workers.sebastiaan-ba3.mcpgateway/tools
Doormat Capital's paid x402 safety tools (token scan, HTTP security headers) for AI agents.
io.github.littleblakew/msds-chainio.github.littleblakew/msds-chain
Chemical safety intelligence — 24 tools: compatibility, hazards, PPE, compliance, SDS lookup
io.github.aapd-studio/omnideckio.github.aapd-studio/omnideck
Local privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls.
io.github.AutomatonColony/automaton-colonyio.github.AutomatonColony/automaton-colony
Screen Base smart contracts and B20 tokens: free on-chain check, paid Flash Audit over x402 (USDC).
dev.lekta/lektadev.lekta/lekta
Audits how AI answer engines read a page and grades it A+ to F across four measured layers.
ai.ssid/ssid-mcpai.ssid/ssid-mcp
Router default logins, compliance index, MAC/OUI lookup. Reads free; submit_correction is Pro.
io.github.CallMarcus/securityscorecard-mcpio.github.CallMarcus/securityscorecard-mcp
Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).
SECONDEDxyz.secondedoracle/seconded-mcp
The oracle for agents. Verify trades, tokens and messages before your agent acts.
io.github.sebastienrousseau/iso20022-evidence-pack-mcpio.github.sebastienrousseau/iso20022-evidence-pack-mcp
MCP server: seal & sign ISO 20022 readiness evidence into tamper-evident audit packs.
io.github.dorianfields/x402-cite-checkio.github.dorianfields/x402-cite-check
Verify cited URLs still resolve: reachability, HTTP status and page title. x402-paid.
au.com.nempulse/nempulseau.com.nempulse/nempulse
Australian NEM battery (BESS) data for AI agents: revenue, dispatch, FCAS, events. Free, no auth.
uk.co.firecompliancecost/siteuk.co.firecompliancecost/site
Fire Compliance Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
uk.co.energyauditcost/siteuk.co.energyauditcost/site
Energy Audit Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
io.github.4hmetuyar/toxic-flow-auditorio.github.4hmetuyar/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
io.github.4hmetuyar/prompt-leak-scannerio.github.4hmetuyar/prompt-leak-scanner
Catches leaked credentials and PII in outbound LLM prompts
io.github.4hmetuyar/secret-scannerio.github.4hmetuyar/secret-scanner
Scans files for leaked secrets and API keys
io.github.4hmetuyar/security-proxyio.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
io.github.voidmobcom/voidmob-mcpio.github.voidmobcom/voidmob-mcp
Mobile proxies, non-VoIP SMS verifications, dedicated numbers, and global eSIMs for AI agents.
corsproxy.devdev.corsproxy/mcp
Call third-party APIs from agents without leaking secrets. SSRF blocked, per-key quotas.
io.github.beepboop2025/groundcheckio.github.beepboop2025/groundcheck
Verify claims, resolve FIGI identity, extract claims, and sign x402 delivery receipts over MCP.
io.github.4hmetuyar/elicitation-auditorio.github.4hmetuyar/elicitation-auditor
MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs
io.github.kumoproductions/mcp-cinema4dio.github.kumoproductions/mcp-cinema4d
MCP server for Cinema 4D — entity CRUD, parameter-level access, batched undo, security controls.
ru.scanbase/scanbaseru.scanbase/scanbase
Website compliance checks for Russian personal data law 152-FZ: score, violations, fix instructions.
io.github.geekmarine/mcp-ssl-inspectorio.github.geekmarine/mcp-ssl-inspector
Audits TLS/SSL handshake latency, HSTS headers, and HTTPS availability on the edge.
online.sigmaintelligence/agentlab-servicesonline.sigmaintelligence/agentlab-services
Signed-quality-receipt micro-services for agents; verify before you pay (x402/USDC).
io.github.SoWhatI/vaultshellio.github.SoWhatI/vaultshell
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
io.github.eltociear/skill-audit-mcpio.github.eltociear/skill-audit-mcp
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
io.github.abyssbugg-labs/sourceryio.github.abyssbugg-labs/sourcery
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
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.