"YAML" matching MCP servers:

Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.

MCP server that lets AI agents use the Online Cyber Tools catalogue as a set of native MCP tools.

Security, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.

Converts natural language security requirements into validated Cerbos YAML policies with automated testing and red-team analysis, enabling AI governance with zero-trust guardrails for tool calls, data access, and compliance frameworks.

Security-first MCP gateway for Odoo 17/18/19 — 27 tools, YAML-driven security

Policy enforcement gateway for MCP tool calls, evaluating every tool invocation against declarative YAML policies (allow/deny/escalate-to-human), generating cryptographic hash-chained audit receipts, and including built-in content safety scanning.

ToolMesh is an Apache-2.0, self-hosted MCP gateway written in Go that sits between AI agents and backend systems. It enforces a fail-closed pipeline on every tool call, including per-tool and per-user authorization, server-side credential injection, structured audit logging, and output policies. APIs are declared in YAML with DADL, turning REST endpoints into MCP tools without writing a custom MCP

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.

mcpwall is a deterministic security proxy for MCP tool calls — iptables for MCP. It sits between the MCP client and server, intercepting every JSON-RPC request and enforcing YAML-defined policies.

Enables users to define and run MCP tools using declarative YAML configs with built-in trust enforcement, credential brokering, and tamper-evident audit logging.

An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.

Enables AML/6AMLD compliance for AI systems, including obliged entity classification, KYC/CDD audits, and sanctions screening.

Enables AML screening of blockchain addresses against OFAC SDN lists and chain heuristics, returning risk scores and flags.

Guardrail 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.

Runtime proxy that intercepts and blocks MCP tool calls based on YAML-defined policies, enforcing security rules for AI agents like Claude Code or Cursor.

AML Watcher MCP Server gives AI agents direct, real-time access to AML Watcher's proprietary sanctions, watchlist, and PEP databases. Connect your agentic workflows to 215+ sanctions regimes, 2.6M+ PEP profiles, and coverage across 235+ countries, no complex integrations required.

A security-focused tool that implements least-privilege credential injection for Claude Code by intercepting Bash and MCP tool calls to swap in minimum-privilege tokens. It enables secure execution of CLI commands and MCP operations by matching tool arguments against declarative YAML policies to prevent unauthorized access.

A secure, declarative MCP runtime that turns YAML configs into MCP servers with trust enforcement, credential brokering, and tamper-evident audit logging.

Audits docker-compose.yml files for security misconfigurations, providing severity ratings, remediation text, and YAML fix snippets for AI agents.

Enables controlled diagnostics and limited actions on a VPS through safe, auditable tools instead of an unrestricted root terminal, including read-only checks, basic Docker status, allowed-path file reading/searching, and YAML/JSON validation.