MCP server directory
53,080 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,580 remote servers
- Updated every hour
skilllint — vet an agent skill before you install itlat.rta/skilllint
Vet an agent skill before you install it: structure, triggers, secrets.
agent-audit + page-read (x402)io.github.agent-audit-x402/x402-tools
Pay-per-call page reader, quote check, link check and x402 seller audit. USDC on Base via x402.
UniFi Gatewayio.github.pete-builds/unifi
Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.
Wanhe AI Compliance Checkertop.wanhetools/compliance
AI content compliance: ad-law prohibited words, AI labeling GB45438, EU AI Act Art50, SB1000
Secret Handoffio.github.geland/secrethandoff
Let agents use temporary secrets without receiving their values in chat. Local stdio; Node 22+.
Keyblindio.github.aarifmms/keyblind
Encrypted secrets vault for AI agents. 27 MCP tools resolve secrets at runtime, never leaking them.
Authmcp Gatewaygithub.com/loglux/authmcp-gateway
Auth proxy for MCP servers: OAuth2 with DCR, JWT, RBAC, rate limiting, multi-server aggregation and a monitoring dashboard.
AEO Inspectorcom.aeoinspector/aeo-inspector
AEO scan, 16-engine AI report and one-domain security + AEO report with fixes (x402 USDC).
CHAP Coordinatorio.github.BrightbeamAI/chap
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
Araigithub.com/taniwhaai/arai
Enforces rules from existing agent instruction files (CLAUDE.md, .cursorrules) by blocking prohibited tool calls and logging per-rule compliance verdicts.
Flowiecom.get-flowie/website
Answers about Flowie: platform, ERP integrations, e-invoicing compliance, pricing. Public.
Rounders to Founderscom.rounderstofounders/r2f
Post your build to R2F, the community for poker players building startups. Verify, climb, log.
Geotone — Global News Signalsnews.geotone/geotone
Live global news signals: ranked wire, story timelines, coverage volume/tone/surges. Free, no auth.
Alter Onboardingio.github.AlterAIDev/alter-onboarding
Guide developers from setup through a verified, policy-aware, audited Alter API call.
Blankasio.github.sirsinatoriai-png/blankas
Numbered, signed blank forms for agent-to-agent deals: issue, co-sign, verify and mark.
OT Intel APIio.github.No3men60/ot-intel-api
OT/ICS threat intel for AI agents: 40 tools, pay per call in USDC on Base via x402.
Keeper Secrets Managerio.github.WYRE-AI/keeper-mcp
Read-only multitenant Streamable HTTP bridge over Keeper Secrets Manager's MCP server.
Keyfoldio.github.codewithkolin/keyfold
Use API keys from your Keyfold vault in commands and .env files. No tool returns a secret value.
Declared-vs-Enforced Agent Access Verificationcom.textforagents/declared-vs-enforced-agent-access-verification
Compares declared agent access against actual enforcement per identity class, with drift watch.
Horizun PBI MCPio.github.HorizunGroup/horizun-pbi-mcp
Build, audit and repair Power BI Desktop models and PBIP reports with DAX, TMDL and PBIR.
Diogenes Dev & Data Utilities MCPio.github.stand-out-of-my-sun/diogenes-dev-utilities-mcp
JSON healing, O(n) ReDoS defense, XML prompt compilation, and schema verification tools.
Microsoft Projectio.github.HorizunGroup/horizun-msproject-mcp
Audit, reschedule and author Microsoft Project schedules. No Java, no Project install.
ClassCADio.github.awv-informatik/classcad
Build and verify CAD parts and assemblies with the ClassCAD engine, locally, no server needed.
Truthoundio.github.seadonggyun4/truthound
Validate local data files, summarize profiles and detect PII without returning raw values.
Sign and register statements on a Forestrie logdev.forestrie/register
Sign and register statements on a Forestrie log, verify receipts, buy grants via x402 within caps
Fetch SCITT receipts and on-chain anchors for offline verificationdev.forestrie/resolve
Fetch a SCITT receipt, its genesis and on-chain accumulator for @forestrie/mcp-verify to verify
Verify SCITT receipts from Forestrie transparency logs, offlinedev.forestrie/verify
Verify a SCITT receipt under a trust root you hold — offline, no backend, no key, no network
GenPark Entropy Hallucination Detectorio.github.alphaparkinc/genpark-entropy-hallucination-detector-skill
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an
GenPark JWT Token Verifier & Claims Auditorio.github.alphaparkinc/genpark-jwt-token-verifier-and-claims-auditor-skill
Pure-Python zero-dependency JWT claims auditor and payload inspector enforcing expiry, audience, and
MCP security checks — WARDEN and HISTORdev.modelmarket/mcp-security
Scan MCP tool definitions for poisoning, look up server history, count tool-list tokens. Free.
JFSecureio.github.theone55/jfs
Let AI agents use secrets without seeing them: masked output, every use approved in JFSecure.
mcpcutio.github.RostislavMatov/mcpcut
Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval
Razielio.github.tide-foundation/raziel
MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis
セキュリティIoTソリューションjp.yomitasu/securityiot-theshop-jp
防犯カメラ 監視カメラ ネットワークカメラ どこでもカメラ 住宅・店舗・事務所・駐車場・倉庫・建設現場・農地など…（securityiot.theshop.jp の内容を検索して答える...
vault-askcom.erseni/vault-ask
Request and send secrets for AI agents, end-to-end encrypted and never shown in the chat.
Turbulence Modeling Resourceio.github.pipeworx-io/turbulence-modeling-resource
NASA Langley Turbulence Modeling Resource (TMR) — verification and validation cases for…
agentegressio.github.co2water/agentegress
See which AI agent and MCP server talks to what on Windows, with a rule-based security verdict
Trust Switchboardio.github.paul-salviani/trust-switchboard
Read public privacy policies: dated source excerpts, follow-up questions and change comparisons.
VMware Hardenio.github.vmware-skills/vmware-harden
VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.
Industrial-AIOpsio.github.industrial-aiops/iaiops
Governed OT data tap: 15 field protocols + cross-protocol RCA brain; audit + MOC gating.
Agent Revenue Networkcom.agentrevenuenetwork/agent-revenue-network
Translation, data quality, execution verification and agent utilities over MCP + x402 USDC on Base.
Go-Live Checkcom.dontdeployonfriday/golive-check
Checks HTTP response headers you paste: 7 security checks with copy-paste fixes. No fetching.
ENTIA Entity Verificationio.github.entia-systems-core/entity-verification
Verified business identity for AI agents: 11.3M entities, EU VAT (VIES), BORME, GLEIF. Free trial.
AnyHooknet.anyhook/anyhook
A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.
EyalSecio.github.EyalSec/eyalsec-mcp
Read your EyalSec security events, machines, runs and rules from an AI assistant.
Preflightcom.allthepossibles/preflight
Scans an MCP server for security gaps before your agent connects. Free tier, no signup.
Re-Agents MCPai.re-agents/mcp
Re-Agents.ai tools for AI agents: website audits and your approved company knowledge.
LoginLlamaio.github.joshghent/loginllama
Ask questions about your login security data: risk scores, blocked logins, Tor, VPN and bot traffic.
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.