MCP server directory
53,930 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 34,214 remote servers
- Updated every hour
dev.agentsim/mcpdev.agentsim/mcp
Control plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.
io.github.dockndevai/mcp-debeziumio.github.dockndevai/mcp-debezium
Debezium / Kafka Connect CDC connector management for AI agents — governed, secret-safe.
io.github.johnmwhitman/agent-meshio.github.johnmwhitman/agent-mesh
Auditable multi-agent coordination: fleets, P2P messaging, witnessed receipts, quorum.
io.github.abyssbugg/sourceryio.github.abyssbugg/sourcery
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
io.github.4hmetuyar/compliance-checkerio.github.4hmetuyar/compliance-checker
KVKK/GDPR/CCPA compliance checks for codebases
io.github.4hmetuyar/vulnerability-scannerio.github.4hmetuyar/vulnerability-scanner
Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
io.github.4hmetuyar/mcp-server-auditorio.github.4hmetuyar/mcp-server-auditor
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
io.github.4hmetuyar/dependency-auditorio.github.4hmetuyar/dependency-auditor
CVE scanning for npm/pip/cargo dependencies via OSV
Haulista Load Assistantio.haulista/load-assistant
Calculate required trucks or containers, verify shipment fit, and manage Haulista loading plans.
io.github.jdhart81/regulatory-radario.github.jdhart81/regulatory-radar
California, US, and global climate compliance scans with source-linked deadlines.
com.accuracite/accuracite-mcpcom.accuracite/accuracite-mcp
MCP server exposing AccuraCite's citation verification and finding API as tools
io.github.moxno/ztdsio.github.moxno/ztds
Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.
io.github.moxno/privacyscrubber-mcpio.github.moxno/privacyscrubber-mcp
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
com.babyblueviper/invinoveritascom.babyblueviper/invinoveritas
Second opinion before an irreversible agent action; signed proofs, free verify, public ledger.
io.github.Jam0k/threatclusterio.github.Jam0k/threatcluster
Live threat intel for agents: incidents, actors, CVEs with KEV/EPSS, ransomware leak-site victims.
MingXi Export Controlio.github.mingxi888888-cyber/export-control
China trade compliance: 2026 tariffs, export-control entities, dual-use licenses & FTA origin rules.
io.obsideo/mcpio.obsideo/mcp
Encrypted S3-compatible storage with possession proofs you can verify yourself. 12 GB free.
io.github.markusvankempen/mcp-ticket-demoio.github.markusvankempen/mcp-ticket-demo
MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP.
io.github.msantagiulianab/solana-x402-complianceio.github.msantagiulianab/solana-x402-compliance
RFC 9110 x402 Solana compliance screening and micropayments gateway for AI agents.
io.github.jmshinhwa/webfont-license-auditio.github.jmshinhwa/webfont-license-audit
The 12 licence questions a foundry audit letter asks, run against your CSS
io.github.Jannis-E/x402-mcp-serverio.github.Jannis-E/x402-mcp-server
Pay-per-call x402 tools on Base: web extract/render, burn-once secret vault, chart, GeoTIFF
io.github.YottaMeta/yotta-verify-mcpio.github.YottaMeta/yotta-verify-mcp
Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
io.github.jmshinhwa/lit-binding-xss-auditio.github.jmshinhwa/lit-binding-xss-audit
Finds the lit-html binding positions auto-escaping does not cover, before the component ships
io.github.jmshinhwa/firestore-rules-guardio.github.jmshinhwa/firestore-rules-guard
Audits firestore.rules and storage.rules for public access, expired test-mode dates and missing owne
io.github.jmshinhwa/erb-escape-auditio.github.jmshinhwa/erb-escape-audit
15 rules that find every line in a Rails .erb view where output escaping was switched off or was the
io.github.jmshinhwa/ssdf-attestation-workflow-auditio.github.jmshinhwa/ssdf-attestation-workflow-audit
14 rules, four CISA attestation sections, one workflow file
io.github.jmshinhwa/cra-readiness-auditio.github.jmshinhwa/cra-readiness-audit
Flags the lines in your repo that break the EU Cyber Resilience Act - default passwords, disabled TL
io.github.jmshinhwa/connection-string-secret-auditio.github.jmshinhwa/connection-string-secret-audit
26 rules and 32 safe-replacement snippets for hardcoded connection strings, keys and kubeconfigs acr
io.github.mrfentmen/infisical-mcpio.github.mrfentmen/infisical-mcp
Infisical API: manage secrets via universal auth.
io.github.theprodsde/agent-memoryio.github.theprodsde/agent-memory
Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.
io.github.muzimu217/DeliverKitio.github.muzimu217/DeliverKit
Plan and verify multi-ecosystem packaging (Linux, Windows, macOS, HarmonyOS) for AI agents.
io.github.mrfentmen/jwt-tools-mcpio.github.mrfentmen/jwt-tools-mcp
Decode and verify JSON Web Tokens locally. No network and no key.
io.github.mrfentmen/unicode-security-mcpio.github.mrfentmen/unicode-security-mcp
Local first MCP checks for Unicode confusables, mixed scripts, invisible controls, and...
io.github.mrfentmen/otp-mcpio.github.mrfentmen/otp-mcp
Generate and verify time based one time passwords locally. No network and no key.
io.github.mrfentmen/osv-mcpio.github.mrfentmen/osv-mcp
Use this MCP server to OSV open source vulnerability data and package security checks. Tools...
io.github.mrfentmen/test-shape-mcpio.github.mrfentmen/test-shape-mcp
Audit local test structure using aggregate assertions without returning test names, paths, or...
io.github.mrfentmen/ssl-labs-mcpio.github.mrfentmen/ssl-labs-mcp
TLS security grades from SSL Labs. No key required.
io.github.mrfentmen/secret-hygiene-mcpio.github.mrfentmen/secret-hygiene-mcp
Count secret-like patterns in bounded local files without returning values, keys, paths,...
io.github.mrfentmen/maltiverse-mcpio.github.mrfentmen/maltiverse-mcp
Threat intelligence for IPs and domains from Maltiverse. No key required.
site.marketnow/marketnowsite.marketnow/marketnow
68k+ security-audited MCP skills + free agent trust layer: signed ATC cards, tool gating, audits.
com.vibgrate/mcpcom.vibgrate/mcp
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
io.github.ajeermahmood/bouncer-gatesio.github.ajeermahmood/bouncer-gates
Stops secrets, cross-tenant queries and unsafe migrations before they merge.
Auditable memory (memory3l)io.github.jayzht/memory3l-mcp
Audited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.
io.github.CsoftTarun/gstinapi-mcpio.github.CsoftTarun/gstinapi-mcp
GSTIN verification, GST filing history and HSN/SAC lookup for India.
io.github.jmshinhwa/mcp-config-auditio.github.jmshinhwa/mcp-config-audit
Audit one mcp.json for what an agent config gives away — inline API keys, unpinned npx launches, pla
io.github.jmshinhwa/jest-snapshot-pii-auditio.github.jmshinhwa/jest-snapshot-pii-audit
15 rules that find the real customer data your .snap files committed
io.github.trencinodin-stack/arcstone-mcp-sidecario.github.trencinodin-stack/arcstone-mcp-sidecar
Deterministic execution boundary and reference MCP sidecar for Arcstone Security Stack
io.github.jmshinhwa/hardcoded-credential-auditio.github.jmshinhwa/hardcoded-credential-audit
Open any config file and see every hardcoded credential — and every setting that quietly undoes your
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.