Identity & access management MCP servers

A server here authentication, user accounts, permissions and access control for apps.

Not here: a server that merely requires a login itself.

325servers
168 remote157 localTagged by Odel's AI, which can make mistakes
By GitHub stars, at most two per publisher
  1. Number 1: Unico@codespar/mcp-unicoDEPRECATED: no live endpoint (api.unico.co does not resolve)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.272 GitHub stars.
  2. Number 2: Certta@codespar/mcp-certtaDEPRECATED: no live endpoint (api.certta.com.br does not resolve)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.272 GitHub stars.
  3. Number 3: node9@node9-ai/node9Access control for AI agents and MCP servers: allow, hold for approval, or block each tool callNot assessed yet.Runs on your machine, installed from npm.217 GitHub stars.

Best fit

140 made for this, ranked by starsRemoteLocal
  1. Auth0 MCP Server @auth0/mcpAuth0 MCP Server: Manage Auth0 applications, APIs, actions, logs, and forms using natural language4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.121 GitHub stars.
  2. Hexis @bevel-software/hexisGit-backed platform for skills, tools, and context for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.94 GitHub stars.
  3. Vorim @vorim-ai-labs/vorim-mcp-serverAI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.66 GitHub stars.
  4. Microsoft MCP Server for Enterprise @microsoft/enterprisemcpOfficial Microsoft MCP Server to query Microsoft Entra data using natural language5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.58 GitHub stars.
  5. WorkOS @workos/mcpManage your WorkOS workspace in plain language: orgs, users, SSO, Directory Sync, and AuthKit.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.45 GitHub stars.
  6. Grantex @mishrasanjeev/grantexOAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.33 GitHub stars.
  7. Semrush Appcenter @mcparmory/semrush-appcenterManage subscriptions, users, and send event notifications for Semrush apps6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
  8. ScopeGate @alifanov/scopegatePermission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.17 GitHub stars.
  9. Microsoft 365 Admin @okapi-ca/ms-365-adminMicrosoft 365 administration via Graph API application permissions (read-only by default).6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
  10. Infrabroker @luisgf/infrabrokerSSH & Kubernetes access broker for AI agents; the model never touches a credential.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.13 GitHub stars.
  11. Authentik MCP Server @samik081/mcp-authentikManage Authentik through AI assistants4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
  12. TAP @human/tapCredential isolation for AI agents: placeholder secrets, policy checks, optional human approval.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
  13. Cortex Gateway @wellknownmcp/cortex-gatewaySelf-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
  14. GreenLake users @hewlettpackard/greenlake-users-mcpHPE GreenLake users MCP Server4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
  15. AIMEAT @aimeat/aimeatAIMEAT - the Linux of AI. An open, federated, self-hosted AI operating system you own. MIT.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.8 GitHub stars.
  16. Supabase SelfHosted @smithery/mistersandfr-supabase-mcp-selfhostedManage Supabase projects end to end across database, auth, storage, realtime, and migrations. Moni…9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.7 GitHub stars.
  17. Auth Your Agent @authyouragent/mcpAct for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
  18. MCP Gateway @panossalt/mcp-gatewayMulti-tenant MCP platform with OAuth 2.1, Entra SSO, RBAC and audit logging.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
  19. OneLogin @onelogin/onelogin-mcpMCP server for OneLogin API - manage users, apps, roles, and authentication3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
  20. Odoo Gateway @parth-unjiya/odoo-mcp-gatewaySecurity-first MCP gateway for Odoo 17/18/19 — YAML-driven security, 27 tools6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
  21. Haldir @exposureguard/haldirGuardian layer for AI agents: identity, secrets, audit via MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.

Also touches on Identity & access management

173 where it is one part of a bigger job