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. 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.
-
Enterprise AI governance, policy compliance verification, tool audit logging, and system health checks MCP server.
-
🔌 Exposes Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.
pypi MIT -
hejdar-mcpgithub.com/arkalda/hejdar-mcpupdated this year
MCP server for Hejdar — runtime policy enforcement for AI agents
pypi MIT -
vaikora-guard-mcpgithub.com/data443/vaikora-guard-mcpupdated this year
Model Context Protocol server that enforces deterministic policy on AI tool calls using the Vaikora policy engine.
pypi MIT -
@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 -
arx-mcp-servergithub.com/gethammerpath/arx-mcp-serverupdated this year
ARX MCP Server - Execute 100+ security operations with policy enforcement, audit logging, and human approvals
pypi MIT License -
Policy MCP server (Go) — Qdrant RAG policy enforcement with fail-closed design
NOASSERTION -
Self-hosted AI compliance enforcement — one policy source enforced across Claude Code, Cursor, Copilot & any MCP agent, with git-hook + CI gates and an append-only audit trail
MIT -
policy-copilot-mcpgithub.com/jaybamroliya/policy-copilot-mcpupdated this year
Real-time policy enforcement and governance layer for MCP-based AI agents.
-
policy-proxy-walletgithub.com/csmoove530/policy-proxy-walletupdated this year
Policy-enforced x402 payment proxy for AI agents. MCP server with spending caps, whitelists, cooldowns, and human approval.
-
🚀 AI-powered CI/CD pipeline analyzer for Azure DevOps & GitHub. Automatically enforces security policies, detects vulnerabilities, and posts compliance reports on PRs. Open source DevSecOps automation.
Apache-2.0 ★ 2 -
Governorgithub.com/chonibe/Governorupdated this year
Policy enforcement for MCP tools and AI agents.
MIT -
Capability-gated security reverse proxy and policy enforcer for the Model Context Protocol
MIT -
GlassTape Policy Builder is an AI-powered MCP server (integrating with Cursor, AWS Q, and Claude) that turns natural-language security requirements into production-ready Cerbos YAML policies, enabling security teams to govern AI agents and applications with policy enforcement through automated generation, validation, and red-teaming of guardrails.
Apache-2.0 ★ 3 -
@iflow-mcp/agentwall-agentwallgithub.com/agentwall/agentwallupdated this year
Run AI agents safely on your local machine — policy-enforcing MCP proxy
npm Apache-2.0 -
Policy-as-code enforcement for AI agents: MCP server, CEL policies, git hooks, SARIF, and static analysis guardrails.
AGPL-3.0 -
@agent-shield/mcpgithub.com/kaleb-rupe/agentshieldupdated this year
MCP server for AgentShield — manage on-chain vaults and enforce policies via AI tools
npm Apache-2.0 -
@vaultys/mcp-agentgithub.com/vaultys/vaultysidupdated this year
Policy-enforced MCP server powered by VaultysID — cryptographic authorization and audit trail for every AI tool call
npm MIT -
engineering-governance-control-planegithub.com/ivasik-k7/engineering-governance-control-planeactive
Engineering Governance Control Plane for AI-assisted software development: versioned policy registry, context engine, MCP server, CLI and CI enforcement
Apache-2.0 -
Repo rules enforcement for AI agents. Checks diffs against AGENTS.md conventions and custom policy, and blocks violations before they land.
npm MIT -
@authensor/mcp-servergithub.com/authensor/authensorupdated this year
Authensor MCP Server - Stripe, GitHub, and HTTP tools with policy enforcement
npm MIT -
@vaibot/mcp-servergithub.com/vaibot-io/mcp-serverupdated this year
VAIBot MCP server — governance circuit breaker for AI agents. Classifies risk, enforces policy, and produces tamper-evident receipts for every agent action.
npm MIT -
PromptGauntlet – Red-team arena for prompt injection vs ArmorIQ policy enforcement. Google ADK + Gemini agent, ops-mcp (16 tools), real Allow/Block policies on platform.armoriq.ai. Built for Flow State 2026.
-
Attack. Defend. Verify. Red-team your AI agents, enforce zero-trust policy at runtime, and prove each fix holds in CI. Includes an MCP proxy.
NOASSERTION -
MCP server for Warden: pre-execution security for agents on Base. Guard a token, tx or address (block/review/clear) and enforce per-agent spending policy (allow/hold/deny).
npm MIT -
Conduct AIgithub.com/sseshachala/conduct-clino update data
List agents, trigger workflows, and enforce team AI policies with ConductGuard.
pypi -
Secure SSH access for AI agents via MCP. Execute commands across your server fleet with policy enforcement, network controls, and comprehensive audit logging.
Apache-2.0 ★ 30 -
agentic-contractgithub.com/agentralabs/agentic-contractupdated this year
Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.
cargo MIT ★ 7 -
Policy firewall for AI agents and MCP tools. Intercepts tool calls, enforces allow/deny/ask rules, redacts secrets, validates arguments, and writes auditable logs before agents touch your filesystem, GitHub, browser, or APIs.
Apache-2.0 ★ 6 -
Policy-enforcing MCP server that lets AI coding agents safely read repos, apply patches, and open pull requests across Forgejo, Gitea, and GitLab.
Apache-2.0 -
AI governance MCP server for policy enforcement, cost control, and observability.
npm -
AISentinel by BizDNAigithub.com/kabzhanov/aisentinelno update data
Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.
mcpb -
A deterministic policy firewall for AI agent tool calls. YAML rules, no LLM calls, no risk scores. CLI + MCP server (advisory) + @enforce() decorator (unbypassable). MIT, 46 tests, zero network dependency.
pypi MIT ★ 1 -
A security-first TypeScript/Node.js MCP server for simulated AWS, Azure, and GCP infrastructure, demonstrating policy enforcement, human approval workflows, auditability, and safe agent-driven operations.
MIT -
contextguard-mcpactive
Policy-enforced, workspace-scoped context and memory MCP server
npm MIT -
@roxy-agent/agentsupdated this year
MCP server that proxies all agent actions, classifies risk, enforces natural-language policies, and logs to a local SQLite audit DB. View activity in the hosted dashboard at roxy-agent-web.vercel.app.
npm MIT -
@synod/mcp-serverupdated this year
Synod MCP Server - authenticated agent identity, policy enforcement, and Synod platform connectivity
npm MIT -
mcp-identitygithub.com/zavora-ai/mcp-identityupdated this year
Identity MCP Server — user lookup, groups, MFA, entitlements, access requests, lifecycle tasks with policy-enforced governance
cargo Apache-2.0 -
mcp-analyticsgithub.com/zavora-ai/mcp-analyticsupdated this year
Governed Analytics MCP Server — metrics, dashboards, funnels, cohorts, anomalies, forecasting, and policy enforcement for AI agents
cargo Apache-2.0 -
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 -
MCP server for enforcing organizational policies on AI agents - validates commands, file operations, and code changes in real-time before execution
-
Policy-first AI security assessment planner with scope enforcement, approval gates, and typed MCP foundations.
NOASSERTION -
A plain-English allowance for your AI agents, enforced at PayPal checkout. MCP + PayPal sandbox + AI policy compiler.
MIT -
checkpoint-waf-mcpgithub.com/Presidentsu/checkpoint-waf-mcpupdated this year
MCP server for Check Point CloudGuard WAF Management API — 68 tools for managing assets, profiles, practices, behaviors, zones, triggers, and policy enforcement
Apache-2.0 ★ 1 -
email-mcpgithub.com/bobtheskull-flameeyes/email-mcpupdated this year
MCP server wrapping IMAP/SMTP with persistent IDLE, DKIM/SPF validation, and policy enforcement. 0BSD licensed.
0BSD ★ 3 -
Demo-ready secure MCP server in Go showing policy-based tool enforcement with OPA, observability, and MCP Inspector testing.
-
clawgithub.com/Leeladitya/clawupdated this year
🦞 Governance-first browser control MCP server with OPA policy enforcement. Secure AI-to-browser bridge with PII scanning, context masking, and comprehensive audit trails.
MIT -
hermes-mcpgithub.com/faysal-x-n/hermesupdated this year
MCP Runtime Security Scanner & Compliance Auditor — static config audit, runtime TLS/auth probe, and policy enforcement for MCP servers
cargo Apache-2.0 -
MCP server that enforces GAIN-Coding workflow gates as code — guiding the agent through reviewed, policy-compliant interactions.
MIT -
veridion-nexus-gatewayupdated this year
MCP Governance Gateway for Veridion Nexus — intercepts, audits, and enforces policy on tool calls
npm UNLICENSED -
MCP Server · Expense policy enforcement, receipt parsing, category classification, and duplicate claim detection
MIT -
Policy enforcement layer for AI coding agents — briefing gates, team memory, Git/CI checks
npm Apache-2.0 ★ 5 -
agentgovgithub.com/bdeva1975/agentgovupdated this year
Governance & observability control plane for agentic systems — policy/budget enforcement, audit trail, and MCP integration. Synthetic-data POC.
MIT -
@ekubo/wallet-mcp-servergithub.com/ekuboprotocol/wallet-mcp-serverupdated this year
Local-first EVM wallet MCP server with trustworthy ABI decoding, encrypted custody, policy enforcement, simulation, and EIP-7702 batching
npm MIT -
guardpostgithub.com/cognis-digital/guardpostupdated this year
Runtime agent firewall — PII redaction, rate limits, policy enforcement
NOASSERTION -
Experimental MCP server for safe, policy-enforced Microsoft Teams Phone administration. Active development; not production-ready.
Apache-2.0 -
mona-lexiqlgithub.com/mona-hq/mona-lexiqlupdated this year
Policy-enforced, proof-carrying, multi-tenant text-to-SQL over MCP — the semantic layer as a security boundary.
AGPL-3.0 -
auditguard-mcpgithub.com/ree2raz/auditguard-mcpupdated this year
A 7-stage compliance pipeline that gates every LLM tool call through RBAC, PII detection, policy enforcement, and audit logging — before and after execution.
Apache-2.0 ★ 1 -
Read-only PostgreSQL & MongoDB access for coding agents. Local, fail-closed MCP enforcement with project-scoped policies.
mcpb MIT -
Multi-Agent DevSecOps Pipeline An AI-powered DevSecOps platform that orchestrates multiple MCP agents to scan code, analyze vulnerabilities, enforce security policies, and auto-remediate — all governed through Archestra.