MCP server directory
52,915 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,450 remote servers
- Updated every hour
bot-check: Bitcoin Self-Custody & WorkSats MCPdev.workers.jeffpersons.botcheck/botcheck
Verify Bitcoin PSBTs, addresses, and descriptors; earn or spend WorkSats bearer credits.
Caiseycom.helpforsupport/caisey
Troubleshoot enrolled client PCs from your AI client, with human approval and an audit trail.
Ipqualityscoreio.github.pipeworx-io/ipqualityscore
IPQualityScore MCP — wraps the IPQualityScore fraud-prevention API (ipqualityscore.com).
Iplookupio.github.pipeworx-io/iplookup
IP Lookup MCP — ip-api.com (free, no auth for basic usage)
Ipinfoio.github.pipeworx-io/ipinfo
IPInfo MCP — wraps ipinfo.io (free tier, no auth required for basic usage)
Inaturalistio.github.pipeworx-io/inaturalist
iNaturalist MCP — citizen-science species observations (free, no auth for read-only)
Imgflipio.github.pipeworx-io/imgflip
Imgflip MCP — wraps Imgflip API (free, no auth for template listing)
Imf Portwatchio.github.pipeworx-io/imf-portwatch
IMF PortWatch MCP — global maritime trade & chokepoint signals (free, no auth)
Iconifyio.github.pipeworx-io/iconify
Iconify MCP — wraps the Iconify public API (free, no auth)
Holidaysio.github.pipeworx-io/holidays
Holidays MCP — wraps Nager.Date API (free, no auth)
Edgario.github.pipeworx-io/edgar
EDGAR MCP — SEC EDGAR public APIs (free, no auth)
MCP Server for OSCALio.github.dfkunstler/mcp-server-for-oscal
AI agent tools for Open Security Controls Assessment Language (OSCAL)
rustsdcmcpio.github.mechubsec/rustsdcmcp
Juniper Security Director Cloud MCP server: scoped, audited change control. Rust.
IA-QA — 152 QA & Dev Tools for AI Agentsio.github.JcJamet/ia-qa-toolbox
152 free QA tools for agents: injection scan, evals, RAG, web audits. Smaller packs: /mcp/{pack}.
IA-QA Security — 30 toolsio.github.JcJamet/ia-qa-security
Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
Marrow AI: Control Layer for AI Agentsai.getmarrow/marrow
Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
prodlintio.github.prodlint/prodlint
Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.
Privi Verifyio.github.canoydario847-cloud/privi-verify
Manufacturing lot verification and chain of custody for AI agents, paid per call in USDC (x402).
screenRIG: free digital signage for AI agentsio.github.screenrig/screenrig
Free digital signage MCP server: publish to TVs, schedule, verify with screenshots. OAuth sign-in.
ComplyEdge TrustLint: offline EU AI Act compliance checksio.github.ComplyEdge/complyedge
Offline TrustLint checks: EU AI Act Article 5, Article 50, GPAI, plus GDPR and HIPAA.
Lokalio.github.lokal-id/lokal
Indonesia-ready agents: NIK, phone, Rupiah, regions, postal codes, holidays, and PII masking.
McpHubcom.soflution/mcphub
One MCP endpoint for all your servers: a few meta-tools, Keychain secrets, sandbox, audit, OAuth.
Jarroba Tools · Test auditio.github.Invarato/jarroba-tools-tests
Audits tests instead of writing them: what each one really asserts. 4 tools, local.
Sint Protocolgithub.com/sint-ai/sint-protocol
MCP governance proxy with capability tokens, tiered approvals, fail-closed execution and tamper-evident audit receipts, plus preflight tool-risk scanning.
rust-junosmcpio.github.mechubsec/rustjunosmcp
Juniper Junos/SRX MCP server: scoped, audited, two-person change control. Rust.
KEVWirecom.kevwire/kevwire
Exploited vulnerabilities, critical CVEs, breaches and AI security incidents, with primary sources.
365rwa RWA structured data (Chinese-language RWA intelligence)vip.365rwa/rwa-data
Chinese RWA data: verification, scorecards, issuances, licenses, market, regulatory via x402.
mcpmio.github.getmcpm/cli
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
cheap-eyesio.github.st412m/cheap-eyes
Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source
Ue5 Automationgithub.com/miracle1814/ue5-automation
Unreal Engine 5 Blueprint automation: create, wire and compile Blueprints, author materials and UMG widgets, and verify PIE runtime state.
Corrie Site Checkio.corrie/site-check
Free HTTPS and security header check from Corrie, uptime monitoring for small teams. No auth.
HOL Guardio.github.hashgraph-online/hol-guard
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
WRM PROio.github.vedranius/wrm-pro
Your self-hosted WRM PRO: logs, files, services and commands with approvals and audit.
Ostorlabco.ostorlab/mcp
Query and act on your Ostorlab scans, vulnerabilities, tickets and assets.
rustunifimcpio.github.mechubsec/rustunifimcp
UniFi Network MCP server: scoped tools, audited two-person change control. Rust.
Safe Creative Platformorg.safecreative/platform
Register events with a qualified timestamp and request certifications anyone can verify
Deliverd Screenio.github.deliverd-dev/deliverd-screen
Find and redact personal data and secrets in text before it reaches a model. Local, no account.
verify402io.github.a32116150-ctrl/verify402-mcp
Free x402 preflight gate plus paid on-chain truth checks for AI agents.
inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trailio.github.DanceNitra/inspeximus
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
Metabase MCP (headless)io.github.Serdnaley/metabase-mcp
Headless Metabase MCP: API-key auth, no OAuth. 178 tools, toolsets, stdio or HTTP, all tiers.
ISMS Copilotio.github.tristanroth1/ismscopilot-account
The compliance specialist your AI calls: ISO 27001, SOC 2, GDPR, NIS 2, DORA and more.
ZeroDOMio.github.DevHusnainAi/zerodom
The deterministic attack-surface perception layer for AI security agents
CircuitAgentio.github.mo9652962-ai/circuit-agent-client
AI hardware synthesis: CircuitBlocks DSL, live LCSC parts, industrial DFX audit, stdio MCP server.
Operational Ontologygithub.com/gura105/operational-ontology
Operational ontology reference implementation: tools generated from a typed business domain model, with rule-checked, audited writes to systems of record.
Odile Gatecom.odilelabs/gate
Free, no signup: your agent puts each app on its own key, allowed calls, approvals and an audit log.
CodexGuildcom.codexguild/codexguild
What changed in your stack since the model's cutoff, error fixes, and security-scanned skills/MCPs
Kremisgithub.com/TyKolt/kremis
Local deterministic knowledge graph on redb with no LLM or embedding calls, BLAKE3 state hashing and canonical export for byte-identical audits.
pracht dev-mcpio.github.JoviDeCroock/pracht
Inspect, verify, diff, and scaffold a pracht app's routes, API, and capabilities from its app graph.
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 27, 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.