"YAML" matching MCP servers:

Simple MCP Runner makes it effortless to safely expose system commands to language models via a lightweight MCP server—all configurable with a clean, minimal YAML file and zero boilerplate.

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

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.

Turn a PowerLab homelab/enterprise host into a structured, agent-driven surface for catalog browsing, app management, system observability, and compose-yaml authoring.

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.

Serves a strictly read-only mail archive over MCP: ordered filter rules pull matching messages from any IMAP mailbox or the Gmail API and write them to disk as byte-faithful .eml plus markdown with YAML frontmatter. Exposes list_rules, list_messages, search_messages, read_message (with full-thread reads) and sync; it never sends, deletes or modifies mail.