"Managing Clerk Authorization" matching MCP servers:

Let AI agents find and hire human help: search services, workers and jobs on GoHireHumans. Hiring and payouts need the account owner's authorization.

Biometric authorization for AI agent actions via Face ID on iPhone, enabling secure approval of sensitive actions and credential-safe API calls through vault execution.

Deterministically evaluates whether a proposed agent spend action matches a supplied policy, returning ELIGIBLE, DENY, or STEP_UP with stable reason codes. Provides local policy evidence only, not payment authorization.

Local zero-trust permission gateway for AI agents. Enforces policy-based tool authorization, human approvals, scoped permissions, and cryptographically verifiable audit logs.

Enables autonomous prompt improvement for voice AI agents through feedback analysis, test generation, and iterative testing.

Enables AI agents to interact with BeeBoo's human-in-the-loop infrastructure for managing knowledge bases, requesting human approvals, and tracking work requests. It provides tools for semantic search, authorization workflows, and task creation across platforms like Claude and Cursor.

Enables LLM-driven tool execution with policy-gated authorization, deterministic verification, and replay for radiographic measurement and SQL repair tasks.

AI agent governance through MCP - policy enforcement, quantum-safe audit trails (ML-DSA), multi-party authorization, and compliance reporting for AI agents.

An authorization-first MCP-governed control plane for executing security-tool workflows in explicitly approved, sandboxed environments with auditable campaigns and AI collaboration boundaries.

An MCP server that enforces runtime authorization for tool calls using Stage0 policy validation, preventing AI agents from executing unauthorized actions before they happen.

Enables MCP servers to enforce their own Proof of Delegation by refusing tool calls when authorization is revoked, suspended, or expired, with optional self-check and verification tools.

Enables MCP hosts to verify agent spending mandates and receipts, providing stateless tools for authorization, chain verification, credential verification, and DID resolution.

A reference implementation for creating an MCP server supporting Streamable HTTP & SSE Transports with OAuth authorization, allowing developers to build OAuth-authorized MCP servers with minimal configuration.

Self-hostable control plane for managing the full lifecycle of non-human identities (AI agents), with short-lived credential issuance, attestation, and an MCP authorization gateway for per-tool access control.

An MCP server for agent authorization that tests the full effect surface and enforces control over consequential actions before dispatch, emitting verifiable execution evidence.

Provides a fail-closed MCP bridge to QMT trading terminals, enabling observe-only, simulated, manual live, and limited automatic trading with hard risk controls, two-phase trade intents, and strict authorization checks.

Enables ChatGPT Plus and Codex agents to use DataRelay Link through a published Agent Plugins package, relaying tool calls to the upstream DRLink Server MCP for authorization and execution.

Sensact is a Supabase-hosted remote MCP server that lets LLM clients discover and invoke device capabilities on user-owned devices, using OAuth 2.1 for authorization and Postgres+Realtime as the control plane.

Enforces a deterministic execution boundary where protected side effects occur only after a separate, single-use authorization condition is satisfied, preventing untrusted or nondeterministic producers from causing actuation without explicit consent.

Demonstrates capability-token write authorization for MCP servers, enforcing per-mutation single-use warrants and human confirmations over an in-memory CRM to prevent unauthorized or destructive actions.