- 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.
Propelauth
PropelAuth — independent third-party profile of a public API surface, by API Evangelist. PropelAuth is a B2B SaaS authentication and multi-tenant user management platform purpose-…
Vengtoo Toolkit
Agent skills for Vengtoo — add authorization, manage policies, and secure AI agent tool calls from your coding agent
P0 Security
P0 Security — independent third-party profile of a public API surface, by API Evangelist. P0 Security is a cloud-native Privileged Access Management (PAM) platform that governs ru…
Tessyr
Policy and proof layer for consequential AI agent actions.
Blastdoor
Blast radius control for autonomous agents: capability boundaries, dry-run by default, verifiable kill switches, and an audit trail for every mutation.
Renker Agent Demo
Runnable demo: renker-core-authz secures an AI agent's tool calls (ALLOW/DENY/REQUIRE_APPROVAL) against prompt injection, via an MCP server + tamper-evident audit log
Eunox
A capability firewall for MCP servers: a deny-by-default proxy that enforces which tool calls an AI agent may make (and with which arguments), backed by a signed audit log. One st…
Agent Trust Plane
Authorization and security regression testing for AI agents and MCP tools.
Aie
Agentic Institution Engineering — portable semantics for authority, delegation, revocation, budgets, lifecycle, topology governance and evidence.
Agentsafe Guard
Runtime governance for AI agents. Wrap a tool in three lines; every call is signed and decided outside your process. Blocked calls never reach your code.
Secure MCP Gateway Lab
Secure MCP gateway lab covering authentication, least privilege, rate limiting, auditability, resilience, and integration tests.
Agent Identity MCP
Reference credential plane for agentic systems: per-action scoped credentials, verifier-side authorization, replay protection, audience binding, and tool-call identity boundaries.…
Auth Doctor
Diagnose OAuth discovery problems on remote MCP servers: the 401 challenge, RFC 9728 protected resource metadata, authorization server metadata, PKCE S256, client registration, to…
Governance Proxy
MCP server that sits between AI agents and real systems. Evaluates every tool call before execution. Holds risky ones for human review.
Agentbond
Agent-first governance infrastructure for AI agents — authorization, intent proof, contracts, and settlement.
Authz
Reference middleware for composing Aiyo — the settlement-verified Economic Execution Authorization plane for autonomous systems — above an MCP server. Verify First. Execute Second.
Ritvo
Open-source authority layer for AI agents: who may approve what, how decisions escalate, and the evidence.
Agentauth
OAuth-style delegated authorization for AI agents and MCP servers — scoped, revocable, short-lived tokens.
Aiagent Portable Authorization
Reference implementation of policy-embedded credential authorization for AI agents (arXiv:2605.11487). Issue signed credentials with machine-evaluable constraints, verify at runti…
Syune AI
Governed memory and context infrastructure for AI agents — authorization, provenance, temporal/version control, lifecycle, audit, and reliable model execution.
Mayi
Argument-level authority for AI agent tool calls. Every argument has one owner (app, model, human or derived). Plain deterministic rules, no judging model. Held calls wait for a p…
Server
MCP server for Vengtoo — gives AI agents tools to check authorization, list namespaces, and manage access policies directly from any MCP-compatible client.
Kit
Auth and versioning for MCP servers, solved. Upstream API auth, API versioning, and a one-call OAuth 2.1 Resource Server (JWKS + introspection) on top of the MCP SDK.
Tegata
No description published.