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.
-
mcp-governance-policygithub.com/zavora-ai/mcp-governance-policyupdated this year
Governance Policy MCP server for ADK-Rust Enterprise — policy evaluation, approvals, simulation, and audit evidence
cargo Apache-2.0 -
MCP server giving AI agents a governed port into enterprise data — contextual PII fencing and a full data-movement audit ledger, enforced once at the transport boundary.
MIT -
Safe-by-default MCP server for GitHub Enterprise — orgs, repos, teams, rulesets, security alerts & Actions, with a security-posture baseline and governance controls (read-only by default, org-scoped, audited, human-confirmed).
npm MIT -
EU AI Act governance layer for an enterprise application portfolio: Claude-based risk classifier, evaluation against a keyword baseline, and an MCP server with per-user scope.
MIT -
Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable information, financial account numbers, JWT tokens, and cryptographic keys using deterministic zero-leakage masking.
MIT -
🌉 Maps IBM AS/400 enterprise records into AI-governance evidence — SOX + DORA.
NOASSERTION -
Microsoft Fabric enterprise BI reference build: hot and cold paths, medallion Lakehouse, semantic model, governed data agent (MCP + A2A), Purview-style governance, Terraform + Bicep. Runs offline on synthetic data.
MIT -
@trentapps/manager-protocolupdated this year
Enterprise Agent Supervisor - Rules Engine MCP Server for AI Agent Governance
npm MIT -
Enterprise Agent Supervisor - AI Agent Governance MCP Server with compliance, risk scoring, rate limiting, and audit logging
MIT ★ 2 -
ContextMesh — governed enterprise intelligence platform on AWS: Report → Review → Authorize → Publish → Query. Remote MCP services, IntelligenceReport domain, policy engine, agent adapters.
NOASSERTION -
claude-harnessgithub.com/anotherben/claude-harnessupdated this year
Governance harness for Claude Code & Codex CLI — 57 MCP tools, 45 quality-gate hooks, 64 enterprise skills, HMAC-signed evidence, 2FA infrastructure locks. Vibe prompt in, enterprise quality out.
★ 7 -
Enterprise code governance and AI audit platform. Detects AI drift, enforces organizational standards, and audits AI-generated code with continuous monitoring.
npm MIT -
Governed MCP server, multi-agent A2A orchestration, and AI cost forecasting for enterprise HCM/Financials scenarios — independent portfolio project
Apache-2.0 ★ 1 -
Autonomous multi-agent AI platform for GitHub repository lifecycle management. MoE routing, self-healing workers, LLM mesh gateway, RAG-enhanced context, enterprise governance. [Archived]
NOASSERTION ★ 2 -
synkbgithub.com/Syntax753/synkbupdated this year
A runnable reference architecture for governed enterprise AI - every AI action policy-checked by OPA, audited, and traceable to a source document. 18 containers, one 'make demo'. MCP-native, ISO 27001-mapped.
Apache-2.0 -
Provider-neutral control plane for running LLM agents inside an enterprise: identity, governance, knowledge, model routing and runtime. Hash-chained audit, hybrid RAG, MCP gateway, deterministic eval gate.
Apache-2.0 ★ 1 -
Promethium — independent third-party profile of a public API surface, by API Evangelist. Promethium is an open agentic data platform that gives analysts, business users, and AI agents trusted access to all enterprise data through a single governed layer without moving, copying, or consolidating data.
-
A Python MCP server for governed enterprise tools: safe SQL analytics, policy lookup, and human-approved ticket creation, with role permissions, audit trails, rate limits, and an interactive dashboard.
MIT -
ai-project-os-mcpgithub.com/wuxiaolong123121/ai-project-os-mcpupdated this year
Enterprise-grade AI engineering governance MCP server
pypi MIT -
mcp-acp-workspacegithub.com/zavora-ai/mcp-acp-workspaceupdated this year
ACP Workspace Control Plane — enterprise management of ACP coding delegates with permission gates, patch review, and governance
cargo Apache-2.0 -
mcp-artifact-storegithub.com/zavora-ai/mcp-artifact-storeupdated this year
Artifact Store MCP server for ADK-Rust Enterprise — governed artifact registry with provenance, integrity, and policy-driven lifecycle
cargo Apache-2.0 -
Zdravo — enterprise AI governance infrastructure. MCP server for governed memory, context, and workspace capabilities.
npm MIT -
Enterprise knowledge copilot — grounded RAG chat with citations, source connectors, custom assistants & tools with governance, MCP, per-tenant secrets vault, sandboxed code execution.
MIT -
Governed enterprise AI workspace for private knowledge, reusable agents, integrations, MCP, and hybrid Azure/on-prem deployments.
MIT -
MCP server for RuntimeAI Enterprise — AI governance control plane. Manage tenants, agents, policies, drift detection, and compliance.
npm MIT -
Governed AI execution platform for enterprise agents, durable workflows, policy enforcement, integrations, evaluation and operations.
Apache-2.0 ★ 1 -
Agentic Event Store & Enterprise Audit Infrastructure: Building the immutable memory and governance backbone for multi-agent AI systems at production scale
MIT -
Enterprise AI governance, policy compliance verification, tool audit logging, and system health checks MCP server.
-
SecOps Nexus is an AI-powered enterprise security connector that lets users query, understand, and act on security findings using natural language through Gemini Enterprise. Built with MCP, it provides secure access to enterprise security data with authentication, RBAC, governance, and audit logging.
-
Enterprise Model Context Protocol (MCP) server for Microsoft 365 governance, Exchange mailbox management, Graph API administration, and automated user auditing.
MIT -
Enterprise AI automation control plane — discovers automation opportunities, runs governed agents over MCP, pauses risky actions for human approval, gates releases on evals, and proves ROI. Models trained from scratch, no AI APIs.
-
Enterprise agentic IT/Ops support triage: a multi-step LLM agent with an MCP server, RBAC + human-approval gates, hash-chained audit, RAG with data governance, and an eval-gated CI pipeline. Python/FastAPI + React/TS; runs fully offline.
MIT -
MCP server for RFP compliance matrix generation — requirement extraction, proposal section mapping, gap analysis, and response outlining for government and enterprise bids
npm MIT -
Self-hostable enterprise shared workspace — content, permissions, governance, search and AI access behind one enforced policy boundary. Rust + React, PostgreSQL with row-level tenancy, hybrid vector search, MCP-native. SharePoint-class in purpose; in development, not production-ready.
Apache-2.0 ★ 6 -
bidcraft-research-mcpgithub.com/crawde/mcp-bidcraft-researchupdated this year
MCP server for RFP/proposal market research — competitor intelligence, past award analysis, agency spend patterns, NAICS code lookup, and procurement landscape mapping for government and enterprise bidding
npm MIT -
tenderai-mcp-servergithub.com/dbugom/tenderai-mcp-serverupdated this year
AI-powered MCP server for government & enterprise tender management — RFP parsing, proposal writing, financial BOM assembly, partner coordination
★ 1 -
bidcraft-pricing-mcpgithub.com/crawde/mcp-bidcraft-pricingupdated this year
MCP server for proposal pricing strategy — cost volume building, labor rate analysis, wrap rate calculation, and price-to-win competitive positioning for government and enterprise RFPs
npm MIT -
df-mcpgithub.com/dreamfactorysoftware/df-mcpupdated this year
DreamFactory is a self-hosted platform providing governed API access to any data source for enterprise apps and local LLMs.
oci Apache-2.0 ★ 7 -
honcho-aigithub.com/dadamschi/honcho-aiupdated this year
MCP server that delivers enterprise governance rules, project context, and skills to Claude at development time — with audit logging and policy enforcement.
★ 1 -
Enterprise AI governance for Claude Code - security, monitoring, and approval workflows for AI agents
npm MIT -
Enterprise Agentic Spec-Driven Development (SDD) & Delivery Governance Studio. 100% client-side & zero telemetry. Synthesizes 4-pillar constitutions, STRIDE threat matrices, 6-region compliance rules (US, EU, GCC, ANZ, APAC, PK), and MCP bridges.
Apache-2.0 -
Enterprise governance for AI-agent access to Drupal — policy profiles, field redaction, DLP, tamper-evident audit logging, and HMAC webhooks over MCP / JSON:API / GraphQL.
★ 1 -
Agentic AI system for enterprise incident resolution using LLM agents, RAG, tool calling, MCP, and governed execution.
-
SEOSiri Official enterprise developer portal & Cloudflare edge topology for AI Search Governance, AEO/GEO Analytics, Schema Validation, Core Web Vitals, DNS Security, and Autonomous AI Agent Tooling for Claude Desktop, Cursor AI, and enterprise AI engines.
★ 1 -
Enterprise MCP integration layer for PostgreSQL, Vertica, Airflow, logs, metadata and lineage with governed access controls.
MIT -
openxnet-servergithub.com/synapxnet/openxnet-serverupdated this year
OpenXnet by SynapXnet: enterprise AI employee collaboration, governed MCP tools, evidence chains, approvals, verification, and auditable execution.
AGPL-3.0 -
@cloudverse/aix-mcpupdated this year
AIX — Enterprise AI Decision Engine MCP Server. Decision-only tools for AI agents to inspect, validate, and govern AI workload routing.
npm -
nexatron-mcpactive
Nexatron MCP server — governed enterprise-data access for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible AI client. Exposes 12 tools (query, list_connections, get_schema, list_metrics, list_views, search_knowledge_base, detect_schema_drift, test_connection, list_conversations, get_report, get_credit_balance, whoami) and 1 resource (nexatron://platform/info) over the Nexatron REST API with per-tenant isolation and cryptographic audit.
pypi MIT -
A distributable Model Context Protocol (MCP) server for Blue Prism v7 Enterprise. It gives an LLM agent governed access to a Blue Prism estate over the supported v7 REST API — work queues, sessions, schedules, resources, processes — with optional, governance-gated control actions.
pypi Apache-2.0 -
Enterprise Multi-Agent AI Operations Platform with RAG, MCP, long-term memory, governed business agents, and workflow orchestration.
MIT -
@adsim/wordpress-mcp-servergithub.com/georgesadsim/wordpress-mcp-serverupdated this year
Enterprise WordPress MCP Server — 137 tools, modular architecture, governance, audit trail, WooCommerce, Schema.org, multilingual.
npm MIT -
Reference architecture exploring governance patterns for AI systems using the Model Context Protocol (MCP) when interacting with enterprise platforms, with a focus on policy enforcement, auditability, and control-plane design.
-
Enterprise-grade Agentic AI customer support engine — LangGraph multi-agent orchestration, hybrid RAG, CNN visual defect inspection, MCP tool protocol, HITL governance, Dockerized.
★ 4 -
Subscribe to an expert, not a prompt — a marketplace of protected expert avatar Agents served over MCP, with an anti-distillation shield, provenance, KYC, enterprise governance, and a community forum.
NOASSERTION -
Enterprise device analytics with a governed AI assistant: DuckDB medallion pipeline, read-only MCP tools for Claude, evals, human-approved briefings and a live React app. Synthetic data.
-
Evidence-first MCP system for adaptive context selection over enterprise-style data, with governed retrieval, Qwen3-4B evaluation, robustness diagnostics, and reproducible evidence.
-
mcp-servergithub.com/YashwinReddy29/mcp-serverupdated this year
MCP server giving AI agents governed access to enterprise data through 6 tools over PostgreSQL and Redis. 5,000 invocations per hour at under 50ms p99, Redis caching with 5 minute TTL, 3 tiered API keys, and full audit logs.
-
AI agent skills for enterprise architecture (Claude Code plugin + MCP server): interviews and docs into validated ArchiMate 3.2 models, views, ISO 42010 docs and governance, in git.
MIT ★ 3 -
Production-Grade-Agentic-MCP-Systemgithub.com/YashhMahajan/Production-Grade-Agentic-MCP-Systemactive
Scout MCP is an enterprise-oriented MCP server with a four-agent support copilot. It gives AI agents policy-governed, tenant-isolated access to PostgreSQL, Elasticsearch, Qdrant, and S3-compatible storage, with human approval for sensitive actions and built-in reliability, auditing, and observability.
MIT -
Enterprise-grade Python + React reference app for vendor-agnostic quote-to-cash agentic decision support, using MCP adapters to assemble live CRM, CPQ, Order Management, Subscription, and Install Base context into a canonical schema for auditable renewal risk, pricing, and governance decisions.