MCP server directory

59888 public MCP servers from the official MCP Registry (26001 from verified domains, 33887 community). Search, filter, copy a setup snippet. Nothing here is installed by cosmic-mcp.

Community listing. Not installed or verified by cosmic-mcp. Check the source before you run anything.

Search servers

Search

Showing 901 to 930 of 1125

• mcp-ssh-manager

  io.github.bvisible/mcp-ssh-manager

  SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail

  Community npmstdio fileshealthsecurity

• mcp-tenant-isolation

  io.github.subodhkc/mcp-tenant-isolation

  Static analysis scanner for MCP server code and multi-tenant SaaS applications.

  Community npmstdio security

• mcp-threatintel

  io.github.aplaceforallmystuff/mcp-threatintel

  Unified threat intel - OTX, AbuseIPDB, GreyNoise, abuse.ch, Feodo Tracker

  Community npmstdio security

• mcp-usage

  io.github.Rixtayz/mcp-usage

  Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.

  Community npmstdio ai-modelssecurity

• mcp-warden

  io.github.ermoluk/mcp-warden

  Local credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.

  Community npmstdio security

• mcp-watchdog

  io.github.bountyyfi/mcp-watchdog

  MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.

  Community pypistdio security

• mcpaudit

  io.github.CloudCorpRecords/mcpaudit

  Audit any MCP server: handshake, schemas, descriptions, error handling, scored.

  Community npmstdio security

• mcpcheck

  io.github.joeyough/mcpcheck

  Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.

  Community remotestreamable-http security

• mcpcheckup

  io.github.fpetitit/mcpcheckup

  Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP.

  Community remotestreamable-http project-managementsecurity

• mcpcut

  io.github.RostislavMatov/mcpcut

  Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval

  Community npmstdio security

• mcpm

  io.github.getmcpm/cli

  MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

  Community npmstdio ai-modelsdeveloper-toolssecurity

• mcpsentry

  io.github.Roshan6335/mcpsentry

  Security scanner and runtime proxy for MCP servers.

  Community npmstdio security

• mcpshield

  io.github.MCPShield-Dev/mcpshield

  Security scanner for MCP servers - detects tool poisoning and injection

  Community npmstdio security

• mcpwall

  io.github.behrensd/mcpwall

  iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.

  Community npmstdio monitoringsecurity

• mcpwatch

  io.github.lazymac2x/mcpwatch

  Audit MCP servers from inside Claude Code. 10 OWASP checks, A-F grade, live leaderboard.

  Community npmstdio ai-modelssecurity

• meek_defoneos_audit_logging_mcp

  io.github.CSOAI-ORG/meek_defoneos_audit_logging_mcp

  MEEK DEFONEOS Audit Logging MCP — SIEM + audit chain + compliance logs. MIT-licensed.

  Community pypistdio securitymonitoringlegal

• megalinter

  io.github.DownAtTheBottomOfTheMoleHole/megalinter

  MCP server for running Ox Security MegaLinter via mega-linter-runner

  Community npmstdio security

• meld

  io.github.lemonaide152/meld

  Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets.

  Community remotestreamable-http security

• memalyze

  io.github.mahaoboy/memalyze

  Self-hosted agent memory: redaction before write, append-only audit, local embeddings.

  Community memorysecurityvector-search

• memdocs

  io.github.silversurfer562/memdocs

  Git-native project memory for AI assistants with enterprise-grade audit compliance

  Community pypistdio legalmemorysecurity

• memi

  io.github.sarveshsea/memi

  Memi is the read-only design engineering audit and skill layer for coding agents.

  Community npmstdio designsecurity

• memory-industry

  io.github.LeandroPG19/memory-industry

  MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.

  Community npmstdio memorysecurityvector-search

• memory-pulse

  io.github.t-crew/memory-pulse

  Give any agent self-improving memory you can trust in production. Built-in memory security.

  Community npmstdio memorysecurity

• meok-ai-psych-vuln-audit-mcp

  io.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

  Community pypistdio legalsecurity

• meok-mcp-injection-scan-mcp

  io.github.CSOAI-ORG/meok-mcp-injection-scan-mcp

  MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026

  Community pypistdio security

• meok-tacho-audit-mcp

  io.github.CSOAI-ORG/meok-tacho-audit-mcp

  UK haulage tachograph audit + drivers' hours + DVSA OCRS Red prevention. Smart Tachograph 2 (July

  Community pypistdio security

• meridian-mcp

  io.github.KNambiarDJsc/meridian-mcp

  Local-first compliance scanner for DPDPA 2023/2025, RBI FREE-AI, SEBI AI/ML & EU AI Act.

  Community pypistdio legalsecurity

• mindforge

  io.github.sairam0424/mindforge

  Read the MindForge engine over MCP: knowledge graph, project health, and audit log.

  Community npmstdio memoryhealthsecurity

• mitre-atlas-mcp

  io.github.CSOAI-ORG/mitre-atlas-mcp

  MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...

  Community pypistdio security

• mova-flat-runner

  io.github.mova-compact/mova-flat-runner

  Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.

  Community npmstdio ai-modelsautomationsecurity

Source: the official MCP Registry (registry.modelcontextprotocol.io), refreshed daily, plus public GitHub data. "Verified domain" means the publisher proved the namespace's domain to the registry; it is not a review. Machine-readable: /v1/directory/servers.