MCP server directory
53,689 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 34,011 remote servers
- Updated every hour
Agent Decision & Evidence Tools (MCP + x402)io.github.PatrickPi1312/eu-compliance
40 MCP tools: multi-chain RPC, market and transaction decisions, AI, EU compliance and US imports
agenteconomy.cloudcloud.agenteconomy/mcp
x402 seller trust for AI agents: verify on-chain revenue, check delivery, diagnose listings.
Power Expert India Regulatory Tariff MCPcom.powerexpertindia/tariff-mcp
Indian electricity tariff and bill-verification MCP with fail-closed regulatory execution.
meek_defoneos_audit_logging_mcpio.github.CSOAI-ORG/meek_defoneos_audit_logging_mcp
MEEK DEFONEOS Audit Logging MCP — SIEM + audit chain + compliance logs. MIT-licensed.
csoai-governance-crosswalk-mcpio.github.CSOAI-ORG/csoai-governance-crosswalk-mcp
Csoai Governance Crosswalk MCP server. Tools: query crosswalk, crosswalk bridge, compliance gap anal
meok-ai-psych-vuln-audit-mcpio.github.CSOAI-ORG/meok-ai-psych-vuln-audit-mcp
EU AI Act Article 5(1)(f) gambling-vertical compliance audit MCP. Detects AI systems that exploit ps
ai-bom-mcpio.github.CSOAI-ORG/ai-bom-mcp
AI Bill of Materials (AI-BOM) generator + auditor MCP — CycloneDX ML-BOM, SPDX 3.0 AI profile, EU AI
meok-compliance-passport-mcpio.github.CSOAI-ORG/meok-compliance-passport-mcp
Agent Compliance Passport MCP server - portable, signed credentials AI agents carry to prove complia
Kaidnio.kaidn/kaidn-mcp
Explain fraud verdicts with evidence, surface account rings, and see who has burned other operators.
MANDATE Credential Brokerio.github.projetnanocorp/mandate
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
Vigil — an outside witness for AI agentscom.vigilnotary/vigil
Agent leases, signed receipts, watchdogs, and optional paid source-verification evidence.
VerifyMCPio.verifymcp/mcp
Independent trust scores, tool surfaces and change history for MCP servers.
HORIZON SHIELD YAKUMO (verified contractor directory)io.github.ogasurfproject-jpg/hs-hearing
Neutral, verification-gated MCP directory of Japan construction contractors (KIRA-audited).
Solar Quote Audit — Check Before You Signio.github.janoliverautomation-stack/solarquoteanalyzer-com
Free independent solar proposal review tool for California homeowners. Audit your solar quote for pr
AI Recommendation Readiness Audit | The Black Friday Agencyio.github.janoliverautomation-stack/canairecommendmybusiness-com
Can AI confidently recommend your business? The AI Recommendation Readiness Audit shows whether your
nomue Record Verifierio.github.licklider-ai/nomue-mcp
Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle.
Verify APIio.github.mgdsn/verify-api-mcp
Evidence-backed verification for citations, packages, repos, cases, filings, drugs, x402 sellers.
Strac MCP DLPio.github.strac-io/strac-mcp-dlp
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
Recall Kitchenio.github.adamdecaf/recall-kitchen
US recalls MCP: free API key/signup or x402 $0.025 Base; some tools need key; verify↑limits
Nizhcom.nizh/nizh
Compliance frameworks (SOC 2, ISO 27001, CMMC, NIST, more) delivered to AI agents as MCP tools.
FillTrust security questionnaire corpuscom.filltrust/questions
Guidance for answering vendor security questionnaires. Every result carries the page it came from.
Security Intel MCPcom.datakoot/cve-vulnerability-lookup
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
SpendShieldio.github.felixpg13-glitch/spendshield
Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.
KnownGatecom.knowngate/verify
Food verification for people and AI agents: evidence-backed verdicts, with sources and dates.
Fallaxio.fallax/fallax
Fallax is a phishing simulation and security awareness training platform. Read your results.
TookEffectio.github.tookeffect/tookeffect
Independent effect verification and signed receipts for consequential AI agent actions.
Strixai.strix/strix
AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets.
SPARDAio.github.zakariagharzouli/sparda-mcp
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
Chapaio.github.juan294/chapa
Read, compare, and verify public developer impact profiles and Chapa badges.
Probe V0io.github.lexbritten/probe
Experimental MCP server for current empirical verification of explicit public HTTPS endpoint claims.
Weav Customer Serviceio.github.dubdubdubco/weav-customer-service
Explore Weav customer service pricing, features, comparisons, signup, and demos. No auth required.
bsv.cxcx.bsv/bsv-cx
Timestamp & verify evidence on-chain, free. Proofpack: a portable BEEF+BUMP proof bundle per txid.
Hookdendev.pages.hookden/hookden
Webhook capture bins for agents: get a URL, wait for webhooks, set replies, verify signatures.
MUJ428 Trust Layer — VERIFY BEFORE ACTio.github.wmujahid428-web/trust-layer
MUJ428 verifies intent and evidence before consequential AI-agent actions.
vat.support VAT Complianceio.github.vmalyshev1/vat-support
EU/UK VAT compliance for AI agents: number validation, rate lookups, reverse-charge checks.
Stipple — Reference Verificationsh.stipple/openwarrant-verify
Fact-check citations: resolve, match, support claims. Arithmetic rechecked. Free to start.
ProfitCollectorca.bakhour/profitcollector
22 pay-per-call developer, security, network and data utilities using x402 on Base.
AI Workstation Open Source Intelligenceio.github.zxhwolfe-dev/aiworkstation-open-source-intelligence
Read-only AI project discovery, verification, comparison, shortlisting, and stack planning.
MERCATOR Verifyio.github.Arzuo/mercator-company-verification
MERCATOR Verify: evidence-backed verification and decision support for autonomous agents.
MCP x402 - Evidence-Backed Web Verificationio.github.Diogoup26/mcp-x402
Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.
DarkMatterio.github.darkmatter-hub/verifiable-agent-audit-trail
Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link.
OutAgentio.github.AAAIStudio/outagent
Pay-to-rank board where agents discover other agents by bid. Bearer auth required.
One-Page Readiness Check — 10 Signals, Arabic or Englishai.advisorsai/store-readiness
Ten machine-readable signals on one public page: the top miss if any, and a receipt we re-verify.
The Stochastic Parrotio.github.portneymk/stochastic-parrot
Span-grounded audits of how US outlets covered the same story, quotes checkable at the source.
AIShield Security Scannerio.github.lm203688/aishield
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
Rosey – Quality verification for human and AI contentcom.getrosey/rosey
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
Agent Runtime Proofio.github.fantasyce/agent-runtime-proof
Verify whether a local Agent or MCP runtime matches an approved artifact.
Security Recipesio.github.stevologic/security-recipes
Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
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.