MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Australian AI governance framework mapped to the Privacy Act and sector laws your AI use triggers — MCP server metadata
NOASSERTION -
RSCT Workflow Framework — memory + MCP governance that stops AI coding agents from skipping plans, bypassing authorization, or breaking conventions.
MIT ★ 3 -
archon-mcpupdated this year
ArchonMCP: A governance framework server for AI-assisted development
pypi MIT License -
Official ACF® Model Context Protocol server: Agentic Commerce Framework® governance copilot for AI assistants.
npm MIT -
MCP, RAG and Skills in one Azure agent (Functions MCP server, AI Search, Agent Framework skills), with the governance control per layer. azd up and go.
MIT -
@iflow-mcp/samrajtheailyceum-ai-governance-mcpupdated this year
MCP server for AI governance laws, regulations, and frameworks
npm MIT -
AI-powered meok governance engine MCP server for agents. Supports full governance report, which frameworks apply, compliance cost estimator. By MEOK AI Labs.
pypi MIT License -
App-first AI framework with a built-in, governed memory engine (memory, agents, RAG, MCP)
MIT ★ 4 -
@l-agence/mcp-server-agencegithub.com/l-agence/agenceupdated this year
MCP server for Agence — AI governance framework with policy enforcement, skills, memory, and multi-LLM consensus
npm MIT -
🌉 Maps UK AI Bill 2026 records into AI-governance evidence — 5 principles framework.
pypi MIT -
🔌 Exposes NIST AI Risk Management Framework over MCP — MAP, MEASURE, MANAGE, GOVERN functions, risk register, trustworthy AI assessment.
npm MIT -
Open-source platform connecting AI assistants to government open data — MCP server, curated civic MCP directory, and anti-hallucination framework for all 559 Socrata portals
npm MIT ★ 48 -
agentstategithub.com/xl-1995/agentstateupdated this year
The open, governed state layer for AI agents — trustworthy, not smarter. The model proposes; a deterministic engine decides; every change is an event. Sits under any agent framework, MCP-compatible.
Apache-2.0 ★ 1 -
techlab-ai-portfoliogithub.com/TechLabAI/techlab-ai-portfolioupdated this year
AI Engineering Portfolio — TechLab AI Framework: hybrid RAG, MCP servers, multi-agent pipeline, human-in-the-loop governance
-
MCP server for AI compliance audit trail and governance. 75 tools, 93 frameworks, 47 provider adapters. EU AI Act, NIST AI RMF, GDPR, CMMC, ISO 42001, OWASP Agentic Top 10, OWASP MCP Top 10, SR 11-7, NIS-2, EU Battery Reg, FERC. Adapters for OpenAI, Anthr
npm Apache-2.0 -
nitrostack-wealth-management-mcpgithub.com/babuvenky76/nitrostack-wealth-management-mcpupdated this year
Production-grade Wealth Management module built with NitroStack MCP framework & MongoDB — portfolio health, policy-governed rebalancing, vector search, interactive widgets. Demonstrates the ease of building AI-powered financial tools with NitroStack.
MIT ★ 1 -
Deep health checks for modern AI infrastructure — 44 company profiles across 5 regions, 14 compliance frameworks, governance auditing, MCP integration, and trend dashboard
MIT ★ 1 -
Swedish government cybersecurity standards MCP -- 16 frameworks from MSB, DIGG, SAPO, CERT-SE, PTS, FI, IMY, Socialstyrelsen, NIS2, Energimyndigheten, Transportstyrelsen. Part of the Ansvar MCP Network (ansvar.ai/mcp)
npm Apache-2.0 -
Data pipelines aren't AI-ready until they are governed: this Databricks framework powered by Apache Spark and PySpark uses Unity Catalog and Delta Lake to serve verified, audit-ready data products through strict read-only MCP boundaries.
MIT -
Model Context Protocol server for Framework-RAI with MCP-compliant endpoints for responsible AI analysis
npm MIT -
Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.
npm MIT ★ 2 -
Read-only MCP endpoint for the Context Stack: discover the framework, route a problem to the right layer, and read canonical sources.
Apache-2.0 -
Remote approvals, policy checks, and execution evidence for unattended AI agents.
npm MIT ★ 318 -
agentgategithub.com/selfradiance/agentgateupdated this year
Collateralized execution engine for AI agents: bond-and-slash accountability with Ed25519 identities, bounded exposure, and progressive trust tiers.
MIT ★ 5 -
kernelmcpgithub.com/gashel01/kernelmcpupdated this year
Governed orchestrator for AI agents — one enforcement chokepoint for budget, RBAC, DLP secret-redaction and audit. Python lib · CLI · MCP server · FastAPI.
pypi Apache-2.0 ★ 1 -
🧭 Orchestrates 13 regulatory frameworks through one MCP with signed audit receipts. MIT.
MIT -
OCTALUMEgithub.com/Harery/OCTALUMEupdated this year
AI-native SDLC framework for regulated industries. 8 phase-gated stages, 9 specialized agents, built-in HIPAA / SOC 2 / PCI / GDPR scanners. Plugs into Claude Code via MCP (30+ tools). MIT, self-hostable. pip install octalume.
MIT ★ 2 -
🔌 Exposes 13-framework × 52-article regulatory crosswalk (NIST AI RMF ↔ ISO/IEC 42001 ↔ EU AI Act ↔ DORA ↔ NIS2 ↔ GDPR ↔ MiCA ↔ Solvency II ↔ HIPAA ↔ SOX ↔ PCI-DSS ↔ CRA). Part of the CSOAI Layer-0: 8 protocols · · bleeding edge ·.
npm NOASSERTION ★ 1 -
Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT.
npm MIT ★ 121 -
🔌 Exposes UK CQC Single Assessment Framework compliance over MCP — KLOEs + NICE NG5 + DSPT.
pypi MIT -
🔌 Exposes Multi-agent negotiation framework. Propose deals, evaluate offers, run auctions, and optimize outcomes. By MEOK AI Labs.
pypi MIT -
🔌 Exposes AI Safety evaluation toolkit: care scoring, threat detection, burnout analysis, relationship prediction, and care membrane probe framework.
npm MIT -
free, open-source plugins for Claude Code & Cowork — Google Drive, WhatsApp, YouTube, WordPress, Apollo & more. Built on the SOSA™ security framework.
MIT ★ 11 -
Model Context Protocol (MCP) server for Decision Keep's out-of-band forensic witness. Lets AI coding assistants, agents and orchestration frameworks natively verify decision trails without pipeline latency.
npm MIT -
Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.
npm MIT ★ 1,094 -
Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.
rubygems NOASSERTION ★ 8 -
Read-only MCP server for the AI Adoption Controls Framework (AACF): controls, Level 3 criteria, cross-references to ISO/IEC 42001, NIST AI RMF and the EU AI Act, and self-assessment questions scored on your side. Runs as a Cloudflare Worker at aacf.adriansaxton.com/mcp. Code MIT, data CC BY-SA 4.0.
MIT