A
licenseNot graded
qualityC
maintenanceGates agent tool execution with human approval, audit trails, and replay-resistant permits, enabling safe use of tools in agent loops.
MIT
Why this server?
Directly matches 'permit' in name; gates agent tool execution with human approval, audit trails, and replay-resistant permits.
Why this server?
A permission gateway that grants per-action permissions, audits every call, and revokes keys, closely aligned with permit core concepts.
AlicenseNot gradedqualityAmaintenancePermission gateway that hands an AI agent a scoped MCP endpoint instead of an OAuth token: connect 27 services (Gmail, Google Calendar/Drive/Ads/Search Console, Slack, Notion, GitHub, Jira, Salesforce, HubSpot, Stripe, LinkedIn, X, Meta Ads and more), grant per-action permissions finer than native OAuth scopes, audit every call and revoke a key in one click. Self-hostable, MIT.1915MITWhy this server?
Local zero-trust permission gateway for AI agents with policy-based authorization, human approvals, scoped permissions, and verifiable audit logs.
AlicenseAqualityAmaintenanceLocal zero-trust permission gateway for AI agents. Enforces policy-based tool authorization, human approvals, scoped permissions, and cryptographically verifiable audit logs.45Apache 2.0Why this server?
Guardrail proxy with policy engine, human approval gates, time-limited grants, and fail-closed defaults — a strong permission-core fit.
AlicenseNot gradedqualityAmaintenanceGuardrail sidecar proxy between AI agents and their MCP/REST/CLI tools. Policy engine, human approval gates, time-limited grants, rate limiting, and OTEL tracing. One Go binary, one YAML config, fail-closed by default.1Apache 2.0Why this server?
Implements a structured five-level permission ladder for requesting, auditing, and revoking permissions in AI agent systems.
FlicenseNot gradedqualityDmaintenanceOperationalizes Seth Godin's Permission Marketing framework to manage user trust and delegation in AI agent systems through a structured five-level permission ladder. It provides tools for requesting, auditing, and revoking permissions to enable autonomous agent actions within user-defined guardrails.Why this server?
Demonstrates explicit tool boundaries, least-privilege discovery, execution-time authorization, and destructive-action confirmation — core permission principles.
AlicenseAqualityDmaintenanceA compact MCP server demonstrating explicit tool boundaries, least-privilege discovery, execution-time authorization, destructive-action confirmation, and metadata-only audit logs using a local note store.3MITWhy this server?
Open-source permission control plane that scans, enforces, and audits every tool call with code-level policies that prompt injection can't bypass.
AlicenseAqualityDmaintenanceOpen-source permission control plane for AI agents — scan, enforce, and audit every tool call with code-level policies that prompt injection can't bypass.1419Business Source 1.1Why this server?
A self-hostable MCP permissions gateway enforcing a thin policy and audit layer over vendor APIs, ideal for permission-centric use cases.
AlicenseNot gradedqualityBmaintenanceA self-hostable MCP permissions gateway for legal-tech systems that connects legal apps once and exposes only the tools each team member should use, enforcing a thin policy and audit layer over vendor APIs.MITWhy this server?
Accountability layer requiring a named human's signed yes before irreversible actions, plus offline-verifiable trust receipts — aligns with permit enforcement.
emilia-mcp-serverofficial
AlicenseAqualityAmaintenanceThe accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.17653Apache 2.0