opa-mcp-server
Related Servers
Alternatives to opa-mcp-server
- FlicenseNot gradedqualityDmaintenanceAn MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.1-
- AlicenseNot gradedqualityCmaintenanceA Model Context Protocol (MCP) server that provides safe, read-only access to Kubernetes resources for debugging and inspection. Built with security in mind, it offers comprehensive cluster visibility without modification capabilities.45MIT
Related Servers
- AlicenseNot gradedqualityAmaintenanceAn MCP server that enforces authorization by evaluating Rego policies or querying an OpenID AuthZEN-compliant PDP, providing accurate access decisions for AI agents. It includes tools for policy evaluation, AuthZEN evaluation, batch evaluation, and PDP discovery.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables developers to wrap existing MCP servers with a deterministic policy enforcement gate that intercepts tool discovery and tools/call requests over stdio, allowing only authorized calls to reach the downstream server. It supports dynamic tool exposure or hiding, allow/deny/approval-required decisions, configurable error disclosure modes, and Ed25519-signed retry credentials for approved workflows.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnforces deterministic security policies as an inline firewall for MCP server tool calls, with AST-based validation, cryptographic audit logging, and CLI-based evaluation and verification.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server to lint and validate Kubernetes-related manifests(Helm, FluxCD, ArgoCD, Kustomize, etc.)59 PyPIMIT
- AlicenseBqualityDmaintenanceA specialized MCP server that provides expert-level OpenFGA authorization modeling guidance, enabling users to create and manage authorization models for ReBAC systems directly from VS Code.29MIT
- AlicenseAqualityAmaintenanceAn MCP server that exposes governance, trust-scoring, compliance, guardrail, cost, drift, and supply-chain scanning tools and resources to any MCP client over stdio, Streamable HTTP, or legacy HTTP+SSE. It lets agents route every tool call through a deterministic five-way decision (allow, redact, require approval, deny, or quarantine) with hash-chained evidence, human approval workflows, and in-agent trust gates for LangChain, LangGraph, and Google ADK.3037 PyPI2MIT
TDQS
Scored across 52 tools
Most tools have distinct purposes, but several evaluation/explanation tools overlap (rego_eval, opa_query_decision, opa_exec, rego_explain_undefined, rego_explain_decision, rego_eval_with_explain), and opa_config/opa_status are near-duplicates. Descriptions help, but with 52 tools misselection is easy.
All names use snake_case with readable namespace/verb-noun components; prefixes (opa_, rego_, conftest_, mcp_) group tools by subsystem. However, the opa_/rego_ split is not perfectly consistent (opa_exec and opa_bundle_build are CLI-oriented like rego_ tools), and a few names are quite long.
52 tools far exceeds the typical 3-15 range; even for a broad OPA ecosystem toolkit this is an extreme count that will overwhelm agents and increase selection errors.
The surface covers evaluation, formatting, checking, linting, testing, coverage, profiling, benchmarking, migration, bundles, server policies/data, Conftest, schema inference, formal verification, and sharing. Very few obvious gaps remain for an OPA-focused MCP server.