MCP server directory
53,397 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,774 remote servers
- Updated every hour
kdbxio.github.yarrasys/kdbx
Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.
AUN — Agent Upgrade Networkcom.a-upgradenet/aun
Audit AI agents' tool calls, planning and memory; Base on-chain data; pay per call via x402.
secureIT Sicherheits-Checksicu.secureit/security-checks
Kostenlose Sicherheits-Checks ohne Konto: SPF/DKIM/DMARC, Mails, Links, Webseiten, Passwort-Leaks.
Vouchwellio.github.Vouchwell/vouchwell
Read, verify and export a tamper-evident log of what an AI agent did. Read-only.
Gulf AI Dealsio.github.gulfaideals/gulf-ai-hub
Read-only, no-auth: sourced GCC AI deals, AI agent use cases in Saudi/UAE, and Arabic AI tools.
Aegis Security Skillsio.github.drupadsachania/aegis-skills
Read-only library of 24 defensive cybersecurity skills: ATT&CK, ATLAS, DFIR, CTEM and more.
MyOTP.Appio.github.brntech/myotp
Send and verify one-time passcodes over SMS, WhatsApp and Telegram.
MCP Dataverseio.github.codeurali/dataverse
Microsoft Dataverse MCP server: CRUD, FetchXML, metadata, schema, audit, batch and security roles.
SORNKan Services Catalog (สอนกาน)com.sornkan/catalog
Thai web, AI app and LINE chatbot dev services from SORNKan (สอนกาน). Read-only, no auth.
AI 内容合规检查（广告法违禁词 + AI 标识）io.github.Wh-bi/wanhe-compliance
中文内容合规检查：广告法违禁词 + AI 标识规则，逐条给出法条依据。Chinese content compliance: ad-law banned terms + AI labeling.
Tessio age verification statseu.tessio/stats
Read your EU age check stats: pass rate, the funnel, refusal reasons and breakdowns. Read only.
DLL Executionio.github.dllio/dll-execution
Free read-only Base Mainnet transaction Preflight and Verification; no signing or custody.
Toolwritgithub.com/emektor/toolwrit
Policy sidecar for any MCP server: deny-by-default tool allowlist with argument rules, call and USD budget caps, and a hash-chained audit log with RFC 3161 t...
mcp-auditio.github.saagpatel/mcp-audit
Scan, enumerate, and risk-score every MCP server configured on your machine.
APIR Agent Verificationai.apir/verify
Check an AI agent you did not build: is it who it claims, inside its mandate, and what's its record
licenscheckcom.licenscheck/verify
Verify US contractor licenses across states: Clear, Review or Risk, with the reasons.
Jid: the trust API for AI agentscom.jid/jid
Verify a business before an agent pays, signs or buys: registry-cited decision and signed receipt.
rustmistmcpio.github.mechubsec/rustmistmcp
HPE Juniper Mist MCP server: scoped, audited, two-person change control. Rust.
Autopiaio.github.MaydayTrey/autopia
Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth.
sealkeepio.github.munhq/sealkeep
Let AI agents use secrets without seeing them: inject into a command, redact the output.
Enokiai.enokilabs/enoki
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
6Frame Verifyio.github.bret1976/6frame-verify
Pre-launch website QA in 60s via real Chromium. $3/check; agents can pay in USDC (x402).
Secret Santa Rafflenet.secretsantaraffle/mcp
Organise a Secret Santa from Claude or ChatGPT. Matchings never appear in the chat.
Torgix Free Equipment Toolsai.torgix/free-tools
Free equipment tools: cost per hour, repair vs replace, compliance, VIN, recalls, manuals.
RentFiguk.co.rentfig/rentfig
Read-only RentFig data for UK landlords: properties, tenancies, arrears, compliance and P&L.
VITNA – Containment for rogue AI agentsxyz.costrinity/vitna-compliance-preflight
Guard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative
VerifyDeskcom.agenttoolworks/verifydesk
Verify French and UK companies, EU VAT and IBANs; screen OFAC, UN, EU and UK sanctions lists.
Agent Readiness Auditorio.github.asish-singh/agent-readiness-auditor
Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
UK company & compliance datasi.fourzerotwo/uk-business
Companies House, Gazette notices, sanctions screening, LEIs and UK legislation.
makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checksai.makememoneynomistakes/scoreboard
Check before you hire or pay an ERC-8004 agent on Base: track record, reputation and fraud flags.
MCP Complianceio.github.YawLabs/mcp-compliance
CLI tool and MCP server that tests MCP servers for spec compliance
AegisGate MCPio.github.aegisgatesecurity/aegisgate-mcp
Secure MCP server framework with 23 security layers and ML threat detection. Zero deps.
emisardev.emisar/emisar
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
VirusTotalio.github.VirusTotal/virustotal-mcp
Official VirusTotal MCP server: threat reports, file and URL submissions, and analysis recovery.
Zekraio.github.fadymondy/zekra
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
TruthPalio.github.corslet1/truthpal
Verify claims against sources: source verification, citation checking; $0.02 USDC on Base.
Vigíacloud.coredls.vigia/vigia
What breaks between versions, vulnerabilities, compatible versions, EOL dates: npm, PyPI, Rust, PHP.
three.ws Provenanceio.github.nirholas/provenance-mcp
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
OpenWatch Nigeriang.openwatch/openwatch
Security incidents across Nigeria, such as kidnapping and banditry, with sources and confidence.
Localnordio.localnord/localnord
Manage Google Business Profiles for agencies: posts, reviews, rankings, audits and reports.
Bonafido: Business Domain Verification APIdev.workers.cybermax-tools.cybermax/bonafido
Bonafido: is a domain a real business site? Verdict, trust score, risk flags.
Acutis Gatecom.acutisgo/gate
Every AI tool call runs as the person who asked, under your rules, fully audited.
Personal Understandinggithub.com/caix84476-netizen/personal-understanding
Verbatim-first personal memory: hashed word-for-word messages, records linked to their source quotes, anti-fabrication validators and an audit dashboard.
AstraNL local proof NLcom.astranl/local-proof-nl
Verify a place in the Netherlands: a verified local hand checks it, you get a sealed receipt.
Emuluxeio.github.Emuluxe/mcp-server
Launch and verify high-fidelity mobile simulations from an AI agent.
GAIP Procurement Evidence Agentio.github.tjcgraham-rgb/gaip-procurement-verify
Now part of GAIP Witness: tests supplier claims and compares them with published metadata.
ThreatLockerio.github.WYRE-AI/threatlocker-mcp
MCP server for ThreatLocker — zero-trust endpoint protection, allowlisting, and policies.
Blackpoint Cyberio.github.WYRE-AI/blackpoint-mcp
MCP server for Blackpoint Cyber MDR — alerts, threats, and operations.
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 28, 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.