- 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.
Agent Guardrails Spring Boot Starter
Security & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot start…
Overstep
Authorization testing for REST APIs and MCP servers. Declare who may do what as a matrix, and overstep turns it into positive and negative tests that catch BOLA, BFLA, BOPLA and p…
ABSuite Core
ABSuite is the trust layer for autonomous systems, providing evidence, verification, governance, and accountability for intelligent systems.
Kong MCP Oauth2
MCP OAuth2 plugin secures Model Context Protocol (MCP) traffic on AI Gateway using OAuth 2.0 specification for MCP servers
LNSAT
Open-source, pre-release source for policy-governed AI-agent authorization, scoped human approval, audit evidence, and read-only MCP adapters.
OAuth 2.1 MCP Gateway
Self-hosted OAuth 2.1 authorization server and reverse proxy for MCP servers — PKCE-mandatory flows, audience-scoped JWTs, per-tenant access control.
Laravel Model MCP
Auto-expose Eloquent models as policy-enforced MCP tools — safe-by-default CRUD over the Model Context Protocol, gated by your Laravel Policies, scoped to your tenant, and audited.
Authz Spicedb Demo
AI agent tool-call authorization using SpiceDB (Google Zanzibar) via Model Context Protocol (MCP)
Stage0 Authorization
MCP server demonstrating server-side authorization with Stage0 runtime policy validation
Pfc MCP Authority Gap
Execution-Time Authority Integrity (ETAI) for MCP: a runnable demonstration that an agent can act on revoked authority under stateless OAuth, and a verifiable-authority layer whos…
Warder
A policy gate for MCP tool calls. Blocks destructive AI agent actions before they run — as the subprocess your AI client launches, where network gateways can't see.
Sshsign
SSH signing service for AI agents. Scoped authorization, co-sign approval with handwritten signatures, immutable audit trail.
A Map
Cryptographic mandate chains and request signing for AI agent-to-agent trust. No central server. No shared secrets.
Velvet Rope
Test whether blocking one AI-agent route actually prevents the real-world effect. ShadowPath maps and replays alternate authorization paths.
Auth0
Auth0 — independent third-party profile of a public API surface, by API Evangelist. Auth0 (now part of Okta) is a leading identity-as-a-service platform providing authentication a…
Delegated Fidelity
The handshake for agents acting on the open internet. Six layers say the authorization is legal; the seventh asks the only question that matters once it is — is the agent still yo…
Authstack
Authstack allows you to solve authentication and authorization problems building SaaS apps, AI agents and MCP servers
Authorization Bom
ABOM: a portable Authorization Bill of Materials schema and reference toolkit for human, workload, service, and AI-agent access
PermitWeave
Local-first, explainable runtime policy gateway for AI tool calls
Okta
Okta — independent third-party profile of a public API surface, by API Evangelist. Okta is the workforce identity incumbent — its Identity Cloud platform (also called the Okta Wor…
Mcpaccess Auth0 Express
Auth0 authentication middleware for Express-based Model Context Protocol (MCP) servers. Easily secure MCP tools, resources, and prompts with JWT validation, role-based access cont…
Mcpaccess Core
Core library for Model Context Protocol (MCP) access control. Includes essential types, interfaces, and utility functions to build consistent authentication and authorization acro…
Wicket
Simple forward path authorization.
Sample App
FastAPI sample app built on delego — intent-bound action authorization for AI agents
Rzp Guard
A deterministic authorization boundary that stops an AI agent issuing refunds nobody approved. Sits in front of Razorpay's MCP server; measured recall and false-positive cost publ…
Trustlogix
Trustlogix — independent third-party profile of a public API surface, by API Evangelist. TrustLogix is a data security and access governance platform that unifies data visibility,…
Clawvisor
Clawvisor — independent third-party profile of a public API surface, by API Evangelist. Clawvisor is the authorization layer for AI agents — a Y Combinator (Spring 2026) security…
PyAPICheck
Transparent API security discovery: risk scores that cite their reasons, real-traffic cross-referencing, an agent/MCP security graph, behavioral baselining, and Cedar policy gener…
Apoa MCP
APOA authorization for MCP servers — per-tool-call scoping, delegation chains, audit trails
Policy Guard
Policy and safety middleware for MCP servers — authorization, rate limits, confirmation gates, audit logging, and PII redaction.
Zenstack MCP Auth
ZenStack Remote MCP Server with Authorization
Rnv MCP Identity
AIII: an Apache-2.0 reference implementation for AI agent identity. An L1–L3 identity-and-authorization layer for MCP servers built on one principle: resolve or refuse, never gues…
Gateway Reference
Reference implementation of the MCP authorization spec (2025-11-25) for enterprise deployments: an OAuth 2.1 gateway that brokers Microsoft Entra ID, enforces three-layer OPA poli…
Agentlock
An MCP server wrapper that gates tool calls on where a value came from, not what it says. Catches cross-hop prompt-injection laundering.
Yii3 MCP Rbac Bridge
Per-user RBAC for MCP servers: yiisoft/rbac permissions on yii3-mcp tool calls, visibility filtering and session-identity binding
Laravel MCP Auth
Bring-your-own-IdP OAuth 2.1 resource server for the official laravel/mcp package: external token validation (JWT/JWKS + RFC 7662 introspection), RFC 8707 audience binding, scope…
Provenant Examples
Runnable Apache-2.0 examples for Provenant — authorize, hold, or deny what your AI agents do, with a tamper-evident audit trail.
Oauth Starter
A minimal remote MCP server with OAuth 2.1 resource-server authorization, built against the 2026-07-28 spec revision. Tested.
Consent Audit
Consent + audit layer for Model Context Protocol (MCP) servers: scoped capabilities, no implicit privilege escalation, revocable grants, and a user-queryable audit trail. Dependen…
Eczid MCP Readiness
Practical MCP readiness, security and stateless-migration resources for teams moving MCP servers toward enterprise deployment.
Agent Mandate MCP
Verification-only MCP server for Agent Mandate
Laravel Agent Kit
Give an AI agent your Eloquent models, not your database. Field allowlists, per-record policy checks and result ceilings, every one of them failing closed.
Chaperone
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP sec…
Policy As Dataplane
A policy document cannot stop a prompt-injected agent. An in-band classifier catches the tool name and misses the effect. An agentgateway MCP allowlist holds. Three control stacks…
Obstat
An auditable decision record for agent tool calls. The clearance is written down before the call runs.
Boundary Audit
Detects MCP tools hidden from tools/list yet reachable via tools/call; the bundled mock reproduces FAIL and PASS. Actively calls operator-named tools; 11 tests, CI. Does not disco…
Webmcp Sentinel
Server-enforced authorization, human approval, and audit for AI-agent actions — a WebMCP security reference implementation
Idp Auth Peps
AuthZEN 1.0 Policy Enforcement Points for Ping Authorize — Kong plugin, Envoy/Istio/agentgateway ext_authz service, and a Node SDK. REST and MCP.
Thunderid Expense Desk MCP
A working example of MCP server authorization with ThunderID. Scopes, runtime policy decisions, and application rules, with an audit trail showing which layer decided.
Crewai Agentlock
Per-tool authorization for CrewAI agents. Every tool call gated, logged, and cryptographically signed.