- Conduid
- Marketplace
- #authorization
MCP servers tagged authorization
174 live MCP servers tagged "authorization", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with authorization.
Exograph
Build production-ready backends in minutes
Oauth Callback
OAuth 2.0 login for CLI tools and desktop apps: opens the browser and captures the authorization code on a loopback redirect (RFC 8252). Node.js, Deno, Bun. One-line MCP client au…
Python
🔐 Plug-and-play auth for Python MCP servers.
Oauth MCP Proxy
OAuth 2.1 authentication library for Go MCP servers
takleb3rry/zitadel-mcp
MCP server for Zitadel identity management — manage users, projects, apps, roles, and service accounts from AI tools
Synauth MCP
SynAuth MCP Server — Biometric approval for AI agent actions via Face ID
Nia
Nia is a context-augmentation layer for agents, primarily designed for coding agents. It provides them with an up-to-date knowledge base and improves their performance by 27%.
Deepsecure
Effortlessly secure your AI agents and AI-powered workflows — from prototype to production. Get easy-to-use identity, credential, and access management built for fast-moving AI de…
Permit Fastmcp
Permit.io authorization middleware for FastMCP servers
Capiscio MCP Python
CapiscIO MCP Guard - Secure your MCP tools with agent-to-server authentication, authorization, and audit logging
Logto
🧑🚀 Authentication and authorization infrastructure for SaaS and AI apps, built on OIDC and OAuth 2.1 with multi-tenancy, SSO, and RBAC.
Kora MCP Server
kora - MCP server for Kora — give Claude governed spending with zero code
Leash
Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.
Doberman Core
Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
Doberman Core
Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
access
Access, a centralized portal for employees to transparently discover, request, and manage their access for all internal systems needed to do their jobs
OctoBus
A secure local gateway for AI agents to reliably call approved enterprise APIs, tools, and services.
Agent Safe Pipeline
Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), veri…
Awesome Openid Connect
OpenID Connect, the authentication protocol and identity layer on top of OAuth 2.0 used in many SSO and adopted in many social logins (Apple, Facebook, Google, ...etc). Find this…
Keycloak
The Keycloak MCP Server designed for agentic applications to manage and search data in Keycloak efficiently
Kinegrant Protocol
Open authorization and accountability infrastructure for physical AI: short-lived capabilities, local action gates, replay protection, signed receipts, post-quantum ML-DSA-65, fle…
Agent Passport System
Open protocol and TypeScript SDK for AI agent authority: identity, scoped delegation, enforcement before the action, and signed receipts.
Agent Identity Management
The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities. Open source.
Agentic Auth
Agentic Auth: untrusted LLM agent auth boundary (MCP gateway + daemon), approvals, budgets, capability tokens, receipts
Control
Decide which MCP tool calls your AI agents can run: a local gateway with signed policies, one-time approvals and an evidence trail. Experimental alpha. Open source, Go.
Node
Runtime authorization for AI agents — Node.js SDK
Control
Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gateway today; connected-channel supervision…
Agent Gateway
The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm traffic between callers and agents.
Theauth
Auth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
Agent Kernel
Capability-based authorization and policy enforcement for agents using large MCP and A2A tool ecosystems.
Auth Servers
🔒 Reference MCP servers that demo how authentication works with the current Model Context Protocol spec.
Openfga MCP
Model Context Protocol server enabling querying and management of OpenFGA and Auth0 FGA authorization stores for automation, intelligent tooling, and natural language.
Authprobe
authprobe pinpoints MCP OAuth failures
Themoltnet
Accountable authority for autonomous agents
Apoa
Agentic Power of Attorney (APOA) | Authorization infrastructure for AI agents
Capgate
Capgate — runtime authority boundary for autonomous AI agents: the agent proposes, the harness authorizes, the executor acts. Deny-by-default policy, non-transitive delegation, ta…
MCP
Tool-level authorization for Model Context Protocol servers: Better IAM credentials, agents and OAuth tokens.
Keycloak
Model Context Protocol server for Keycloak administration
Sharedos
Model Context Protocol toolshare bridge for SharedOS: the permission-filtered catalogue as an MCP server
Permit MCP Server
MCP Server for Permit.io read-only operations
Smcp Security
Secure Model Context Protocol (SMCP) v1 - Production-ready security framework for MCP implementations
Fga
MCP Server for OpenFGA or Auth0 FGA
Vinctor MCP Pep
Vinctor MCP enforcement proxy (PEP): a stdio MCP proxy that authorizes every tools/call via Vinctor delegated enforcement before forwarding it to the real server.
Governance Proxy
MCP server that sits between AI agents and real systems. Evaluates every tool call before execution. Holds risky ones for human review.
Nominee
Decision-bound Model Context Protocol tool handlers for governed AI agents
Sigilctl
Verifiable authorization receipts for AI agents. Prove what your agents were allowed to do — and what they were denied.
Authz
Authorization for MCP servers: OAuth 2.1 resource server, roles/permissions policy, permission-gated tools (2026-07-28)
Proxy
MAP (Model Context Authorization Protocol) — enforcement proxy for MCP servers
Sso
OAuth 2.1 and enterprise SSO for remote MCP servers without API keys in client configs.
Awesome Node Auth
The Sovereign Identity & Communication Layer for Node.js. Scalable by design. No SaaS/DB lock-in. MCP Server for auto-config in IDE, Hybrid Web/Mobile Auth, Dynamic in/out Webhook…