MCP server directory
53,596 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,938 remote servers
- Updated every hour
Agent DVRcom.ispyconnect/agentdvr
Ask your security cameras anything and set up alert rules in a sentence. Built into Agent DVR.
OpenStelaio.openstela/openstela
Register AI characters and works, bind works to characters, verify fingerprints, read the market.
MemoryLayerin.memorylayer/memorylayer
Local-first persistent memory for AI agents, with reasoning and formal verification.
Shoon A2A Trust Services (pilot)io.github.ShoonEnterprises/shoon-a2a-sandbox
Five trust services for agents: claim checks, citation audits, extraction, tripwires, work audits.
Swampworld.swampai/swamp
An open habitat where security agents register themselves, work in public, and rerun each other.
ATTRACTOR Verification, State & Evidenceio.github.NovanBaillif/attractor-machine-commons
Verify artifacts, hand off public state, and record, check and find evidence about capabilities.
Tkach Securityio.github.ECD5A/tkach-security
Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
Attestio.github.dev-prathap/attest
Decide by policy, gate behind a human, verify by read-back, record a hash-chained ledger.
specpackio.github.THE-KIPDEV/specpack
Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.
Delta Registry — Regulatory & Compliance Monitoring (28 tools)io.github.stefanoseggio/delta-registry
28 pay-per-event tools for regulatory, sanctions, procurement, and corporate-registry monitoring.
Katlaapp.katla/katla
GDPR/CCPA cookie consent: scan sites for cookies, track consent rates, generate privacy policies.
tilwhen date enginecom.tilwhen/tilwhen
Deterministic date arithmetic with auditable receipts: business days, due dates, holidays.
Rule Trade - Japanese equity verification layerjp.ruletrade/mcp
Verified Japanese equity studies: 50 anomalies, 26 indicators, 12 candlesticks, events, ETF decay.
nomue Record Verifierio.github.licklider-ai/nomue-verifier-mcp
Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle.
Keeper Secrets Managerio.github.wyre-technology/keeper-mcp
Read-only multitenant Streamable HTTP bridge over Keeper Secrets Manager's MCP server.
FlowSentryio.github.vasilicasijarvis/flowsentry
Security scanner for n8n workflows + live MCP Trust-Check. 18 rules, OWASP mapped. Paid x402 API.
Nautilus Compass Memoryio.github.chunxiaoxx/nautilus-compass
Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
Czech Company Registry (ARES) Toolsio.github.appvantagelabs2-a11y/czid
Czech ARES company registry: VAT, insolvency, RÚIAN addresses, IČO/DIČ checks. All free, no auth.
Barcode Tools (decode, render, GTIN validate)io.github.appvantagelabs2-a11y/barcode
Decode, render, validate barcodes: QR, DataMatrix, EAN, UPC, PDF417. All tools free, no auth.
MCP Security & Vulnerability Auditorio.github.Ansarii/mcp-security-auditor
Static AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.
mcp-airlockio.github.Shalimov04/mcp-airlock
Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit
numberRankdev.numberrank/numberrank
Is a phone number VoIP or a real carrier line? Line type, score and grade, free, no auth.
Neon Zero-Trust MCP Gatewayio.github.Ansarii/zero-trust-mcp-gateway
AI security firewall & DLP proxy protecting API keys and blocking destructive commands.
Agent Mandate Verificationio.github.API-Disk-Integrations/agent-mandate
Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.
DataCharterio.github.datacharter/datacharter
Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.
Singularity - MCP Discovery & Security Gatewayio.github.gaurav-kumar-sinha-060705/singularity
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
American Trades Indexcom.americantradesindex/american-trades-index
Licensed electrician, plumber & HVAC workforce data by US county: supply, movement, verification.
Factumio.github.factum-project/factum
Auditable memory for AI agents: provenance, cascade retraction, conflict refusal
DocGuardio.github.raccioly/docguard
Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools.
LLM Red-Team Scannerdev.workers.manhliemcn4euwlu.llmrt-companion/llm-red-team-scanner
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
AgentFEMio.github.haoming-luo/agentfem
Build, run, inspect, and verify finite-element simulations with AgentFEM.
ScanLabsAI Security Scannercom.scanlabsai/scanner
Scan a website for vulnerabilities: OWASP Top 10, CVEs, SSL, headers - with plain-English fixes
ssh-mcpio.github.gelse/ssh-mcp
MCP gateway for controlled SSH access with per-client auth, command policies, and audit logging.
TW-Market Live Data Intelligenceio.github.SmartyJohnway/tw-market-live-data-intelligence
Local-first Taiwan market evidence for AI agents: Watchlists, governed MCP, audited execute-once.
nickol-knxio.github.NickoScope/nickol-knx-mcp
Read-only KNX/ETS project auditor: validates a .knxproj and generates Home Assistant YAML
agentguard — policy proxy for agent tool callsio.github.agentwares/agentguard-cloud
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Python Package Runtime Testio.github.ligafew/python-package-runtime-test
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
Nebelus Agent Constructionai.nebelus/construction
Build & govern AI agents for regulated industries: EU/GCC residency, governance, audit.
Fda Risk Radar MCPgithub.com/thehealthai/fda-risk-radar-mcp
FDA and NHTSA regulatory risk data: device compliance risk, 510(k) evidence, predicate chains, postmarket signals, reimbursement pathways and vehicle safety.
OutilsIA — Conseiller IA localefr.outilsia/local-ai-advisor
Read-only local AI advice, shared reports and website audits. No PC scan or local actions.
ONCE — Exactly-Once Reliability for AI Agent Actionsio.github.GSterlingPress/once
Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
Verify China Supplier | Supplier Checkio.github.lu7897859-tech/china-sourcing-audit
Verify a Chinese supplier before you pay: company identity, status, risk signals. x402 per call.
EveryAILawio.github.snapsynapse/every-ai-law
AI law obligations, evidence, deadlines, saved profiles, audit trails, and signed change alerts.
Vizier Guardio.github.vassiliylakhonin/vizier-guard
Deterministic authorization and security guard for AI agent actions with signed receipts.
openfang-railio.github.89rat/openfang-rail
Deterministic banking, LEI, VAT, SWIFT & compliance checks via MCP with signed XDR-1 receipts.
Secret Scanio.github.agentic-income-bot/mcp-secret-scan
Check text for leaked credentials before an agent writes or commits it. Runs locally.
MaskFlow PII proxyio.github.maskflow/mcp
Mask PII in outbound MCP tool-call arguments, unmask the results. Indian identifiers included.
MCP E-Invoicing Coreio.github.cmendezs/mcp-einvoicing-core
Base package for e-invoicing MCP servers. Compliance logic and signing keys stay with you.
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.