"Loop" matching MCP servers:

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

Demonstrates agent-native platform onboarding with human-in-the-loop API key provisioning, plus live usage and rate-limit queries via Anthropic Admin APIs.

A hardened, self-hosted MCP server that lets AI agents query and govern an Infraveil control plane in-loop, reading state and filing deploy/remediation requests that require human approval.

An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.

MCP server that lets AI coding agents (Claude Code, Cursor, Cline) audit Supabase projects for security misconfigurations AND apply the fixes — without leaving the agent. Tools: audit_project, list_findings, preview_fix (BEGIN/ROLLBACK safety), apply_fix (with confirmation), apply_all_fixes (transactional bulk). Closes the audit-fix loop entirely in the agent — other Supabase scanners only report.

Human-in-the-Loop approval gate for AI agents to assess risky operations and require user approval via Cursor forms.

Exposes cQnce human-in-the-loop authorization as MCP tools, letting AI agents request and await human approval for risky actions. Includes request submission, monitoring, and project/team management capabilities.

Free seven-tool proof loop for MCP agents: scoped sessions, bounded authorization, typed outcomes, evidence-bound claims, and tamper-evident local closure. Upgrade to Complete Local for durable memory, recovery, signed traces, release verification, and multi-agent workflows.

Human-in-the-loop approval gateway for agent tool calls: agents request, policies decide, humans approve via Slack/Discord/web — with an OWASP-LLM-Top-10-tagged audit trail. Self-hostable.

A governance and policy enforcement gateway for MCP servers that provides hard guardrails, dynamic parameter bounds, human-in-the-loop approvals, and audit telemetry.

Governance Intelligence Architecture (GIA) is a governance-first MCP server that provides approval gates, auditable decision logs, compliance mapping, and operational safety controls for Claude agents. It connects Claude Desktop and Claude Code to a hosted governance control plane for secure, production-grade AI workflows.

A secure MCP server enabling tool calls (kb_search, read_doc, publish_report) through a zero-trust CapabilityBroker with OWASP LLM Top-10 guardrails and human-in-the-loop approval.

Enables secure Bitwarden organization vault control with AI agents, featuring human-in-the-loop approval, ACID-compliant transactions, and redacted access to keep secrets hidden from LLMs.

Enforces policy controls for AI agents, including spend limits, action approvals, kill switch, scoped credentials, dry-run diffs, loop prevention, and auditable hash-chained logs.

Provides a set of MCP tools to clone and analyze arbitrary MCP server repositories, run static and dynamic security probes in isolated Docker containers, and produce vulnerability verdicts with a human-in-the-loop approval step before filing public reports.

Enables secure support-ticket and customer-account operations with signed JWT authentication, prompt-injection and tool-poisoning guardrails, and human-in-the-loop confirmation for destructive actions.

Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.

Enables AI agents to be governed by formal Gentzen sequent calculus proof trees, with human-in-the-loop approval gates and cryptographic audit trails for consequential actions.

Control-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.