Agent Governance Security MCP Servers

Tools for enforcing policies, access control, audit logging, and safety constraints on AI agents at the protocol level. Includes credential isolation, deterministic policy enforcement, and compliance frameworks. Does NOT include general security infrastructure, secrets management, or agent frameworks themselves.

There are 97 agent governance security servers tracked. 2 score above 50 (established tier). The highest-rated is AndrewAltimit/template-repo at 54/100 with 110 stars.

Get all 97 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=mcp&subcategory=agent-governance-security&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Server	Score	Tier	Stars	Language
1	AndrewAltimit/template-repo Agent orchestration & security template featuring MCP tool building,...	54	Established	110	Rust
2	knowledgepa3/gia-mcp-server MCP proxy for GIA Governance — connects Claude Desktop and Claude Code to...	50	Established	1	JavaScript
3	Chimera-Protocol/csl-core Deterministic safety layer for AI agents. Z3-verified policy enforcement.	49	Emerging	6	Python
4	portofcontext/pctx pctx is the execution layer for agentic tool calls. It auto-converts agent...	48	Emerging	212	Rust
5	agentralabs/agentic-contract Policy engine for AI agents — enforceable rules, risk limits, approval...	46	Emerging	4	Rust
6	postralai/masquerade The Privacy Firewall for LLMs	45	Emerging	74	Python
7	behrensd/mcpwall Deterministic security proxy for MCP tool calls — iptables for MCP	44	Emerging	2	TypeScript
8	Huzefaaa2/terraform-guardrail Terraform-Guardrail (TerraGuard) MCP is an open-source governance framework...	43	Emerging	5	Python
9	openagentidentityprotocol/agentidentityprotocol Agent Identity Protocol - Zero-trust security layer for AI agents. Policy...	42	Emerging	18	—
10	turbot/guardrails-mcp Enable AI assistants to explore and query your Turbot Guardrails data!	41	Emerging	4	TypeScript
11	mcptrust/mcptrust Runtime security proxy for MCP: lockfile enforcement, drift detection,...	40	Emerging	6	Go
12	nshkrdotcom/GUARDRAIL GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation,...	39	Emerging	17	—
13	eqtylab/mcp-guardian Manage / Proxy / Secure your MCP Servers	39	Emerging	193	Rust
14	elliot35/deterministic-agent-control-protocol Governance gateway for AI agents — bounded, auditable, session-aware control...	39	Emerging	145	TypeScript
15	PolicyLayer/Intercept The enforcement layer for AI agents. Intercept enforces hard, deterministic...	37	Emerging	12	Go
16	Sentinel-Gate/Sentinelgate Access control for AI agents. MCP proxy with RBAC, CEL policies, and full...	37	Emerging	5	Go
17	sanna-ai/sanna Trust infrastructure for AI agents — constitution enforcement and...	37	Emerging	1	Python
18	agentralabs/agentic-comm Structured agent-to-agent and agent-to-human communication — channels,...	36	Emerging	3	Rust
19	gbrigandi/mcp-server-conceal Privacy-focused MCP proxy that intelligently pseudo-anonymizes PII in...	36	Emerging	11	Rust
20	vellaveto/vellaveto Agent Interaction Firewall for AI tool calls. Runtime security for MCP and...	34	Emerging	7	Rust
21	randysalars/boardroom-mcp AI Governance-as-a-Service — Give your AI agents a boardroom of 450+...	33	Emerging	—	TypeScript
22	ivanlkf/navil Open-source agent governance middleware. Runtime security proxy for MCP...	33	Emerging	1	Python
23	shleder/toolwall Fail-closed stdio transport firewall for MCP JSON-RPC tool traffic	32	Emerging	1	TypeScript
24	3p3r/oatmeal Oatmeal is a single binary tray application that extends your web agent's...	28	Experimental	5	Rust
25	perfecxion-ai/secure-mcp Enterprise-grade Model Context Protocol (MCP) server with advanced security,...	26	Experimental	1	TypeScript
26	Invasivecape/ghost-protocol 🔍 Eliminate data until revealed with Ghost Protocol, a privacy system that...	25	Experimental	1	Solidity
27	OrelliusAI/orellius-dome Protective Dome for AI Agents — MCP security gateway proxy (Rust)	25	Experimental	3	Rust
28	Orellius/thunder-dome Protective Dome for AI Agents — MCP security gateway proxy (Rust)	25	Experimental	3	Rust
29	vitas/evidra-lock MCP Kill-switch for AI agents. Validates infrastructure operations before...	25	Experimental	7	Go
30	TrentApps-com/ManagerProtocol Enterprise Agent Supervisor - AI Agent Governance MCP Server with...	25	Experimental	2	TypeScript
31	adhit-r/aran-mcp Enterprise-Grade MCP (Model Context Protocol) Security and Management Platform	24	Experimental	—	TypeScript
32	Orellius/mcpdome Protective Dome for AI Agents — MCP security gateway proxy (Rust)	24	Experimental	4	Rust
33	sattyamjjain/agent-airlock Open-source security firewall for AI agents — validates tool calls, strips...	24	Experimental	3	Python
34	apathy-ca/sark Zero-trust gateway for AI systems. OPA policies, audit logging,...	24	Experimental	1	Python
35	CarlosLadd/AgentOx AgentOx - Agentic Tool Security Platform (MCP + A2A + OpenAI tool_use)	24	Experimental	3	Rust
36	Rul1an/assay Policy-as-Code for AI Agents. Deterministic testing, runtime enforcement,...	24	Experimental	1	Rust
37	paolovella/vellaveto Agentic security control plane for MCP and AI agent tool calls. MCP-native...	24	Experimental	3	Rust
38	MaxwellCalkin/sentinel-ai Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection,...	23	Experimental	2	Python
39	SiteWarming/Comply AI-powered open source license compliance scanner. Analyzes how dependencies...	23	Experimental	1	TypeScript
40	kobepaw/goop-shield-community Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP...	23	Experimental	2	Python
41	Bajuzjefe/Aikido-Security-Analysis-Platform Security analysis platform for Aiken smart contracts on Cardano: 75...	23	Experimental	2	Rust
42	NimbleBrainInc/mpak-trust-framework MTF: An open security standard for MCP server bundles. Defines compliance...	22	Experimental	1	Astro
43	InnerWarden/mcp-guard Runtime security for MCP servers and AI agents. Pre-execution guardrails,...	22	Experimental	—	Rust
44	vaddisrinivas/mcp-extras Transparent MCP proxy that gates destructive tool calls behind human...	22	Experimental	—	Python
45	devwebxyn/securemcp-lite A lightweight local MCP firewall for AI agents that enforces YAML security...	22	Experimental	—	TypeScript
46	ElmadaniS/halyn Halyn — Enforceable safety for AI agents. Hardened shields (unicode,...	22	Experimental	—	Python
47	adhit-r/audit-lens AuditLens: The impeccable, agentic compliance engine. Transform evidence...	22	Experimental	—	Python
48	nelsoncc/agent-guard Runtime governance for tool-using AI agents in Java — budget enforcement,...	22	Experimental	—	Java
49	useoverwatch/overwatch The Agent Control Plane — Unified identity, governance, cost control, and...	22	Experimental	—	TypeScript
50	NeuZhou/mcp-firewall Runtime security proxy for the Model Context Protocol (MCP). The Cloudflare...	22	Experimental	—	TypeScript
51	ToolOracle/trustoracle FeedOracle Trust Layer — Verifiable evidence & verification MCP server for...	22	Experimental	—	—
52	provnai/McpVanguard An open-source security proxy and active firewall for the Model Context...	22	Experimental	1	Python
53	kvlar-io/kvlar Runtime security for AI agents — policy engine and MCP proxy	22	Experimental	1	Rust
54	capiscio/a2a-demos Demo agents showcasing CapiscIO Agent Guard and MCP Guard — trust badges,...	22	Experimental	1	Python
55	bigmoon-dev/Aegis MCP governance proxy for AI agents — enforce rate limits, access control,...	22	Experimental	1	Go
56	Hairsplitterketonegroup852/orellius-dome Secure AI agent interactions by managing access and threats through a...	22	Experimental	—	Rust
57	piyushptiwari1/mcpkernel The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement,...	22	Experimental	—	Python
58	yoned0609/AgentGate The authorization layer MCP doesn't have. JIT proxy for AI agents.	22	Experimental	—	Python
59	wd041216-bit/ironclaw-agent-guard Agent-runtime security core with CLI, reusable skills, and stdio/HTTP MCP...	22	Experimental	—	JavaScript
60	vishtechie07/zero-ai-gateway Zero-Trust AI Gateway: Dual-pass PII redaction (Regex + LLM), real-time...	22	Experimental	—	Java
61	capiscio/capiscio-mcp-python CapiscIO MCP Guard - Secure your MCP tools with agent-to-server...	21	Experimental	—	Python
62	LuciferForge/agent-safety-mcp MCP server wrapping ai-cost-guard, ai-injection-guard, and...	21	Experimental	—	Python
63	Vigile-ai/vigile-mcp MCP server for Vigile AI Security — query trust scores for MCP servers and...	21	Experimental	—	Python
64	ido4-dev/ido4 Development Governance Platform — deterministic methodology enforcement for...	21	Experimental	—	TypeScript
65	knortzwellez/shellguard 🛡️ Enable secure, read-only SSH access for LLM agents to audit servers, run...	21	Experimental	—	Go
66	ark-forge/mcp-eu-ai-act MCP EU AI Act Compliance Scanner - Open source tool to detect EU AI Act...	21	Experimental	—	JavaScript
67	steveswain14/mcp-json-suppressor A standalone MCP suppressor that sanitises, validates, and stabilises JSON...	21	Experimental	—	Python
68	steveswain14/mcp-hallucination-suite A unified suite of MCP suppressors that prevent hallucinations, enforce...	21	Experimental	—	Python
69	egoughnour/code-firewall-mcp A structural similarity-based code security filter for MCP (Model Context...	21	Experimental	—	Python
70	wharfe/agentbond Agent-first governance infrastructure for AI agents — authorization, intent...	21	Experimental	—	TypeScript
71	ExpertVagabond/ibmz-mcp-server MCP server for IBM Z mainframe integration -- Key Protect HSM key management...	21	Experimental	—	Rust
72	jellewas/eu-audit-mcp Tamper-evident audit trail MCP server for EU AI Act & GDPR compliance	21	Experimental	—	Python
73	adwantg/mcp-egress-guard Policy enforcement proxy for MCP tool calls: detect leaks, block risky...	21	Experimental	—	Python
74	VikingOwl91/mcp-firewall Security proxy for Model Context Protocol (MCP) servers - policy...	21	Experimental	—	Go
75	iambilliefan/gia-mcp-server Connect Claude AI agents to a governance layer for decision tracking,...	21	Experimental	—	JavaScript
76	sneiko/agent-guard Contract-based accountability runtime for AI agents. Define tasks with...	21	Experimental	—	Go
77	steveswain14/mcp-prompt-suppressor A standalone MCP suppressor that filters, sanitises, and stabilises user...	21	Experimental	—	Python
78	steveswain14/mcp-tool-response-suppressor A standalone MCP suppressor that filters, stabilises, and sanitises tool...	21	Experimental	—	Python
79	ExpertVagabond/guardrails-mcp-server MCP server for AI agent security -- input validation, prompt injection...	21	Experimental	—	Rust
80	steveswain14/mcp-grounding-enforcer A standalone MCP suppressor that enforces grounding by validating...	21	Experimental	—	Python
81	imnumb1/terraform-guardrail 🔒 Enhance Terraform governance with a Python-based MCP server and CLI,...	21	Experimental	—	Python
82	aryan877/mcp-guardian An MCP server that scans, tests, and locks down other MCP servers. Built on...	21	Experimental	—	TypeScript
83	cogniolab/enterprise-mcp-framework Production-grade security, observability, and governance for Model Context...	21	Experimental	2	Python
84	razashariff/mcps MCPS -- MCP Secure. Cryptographic identity, message signing, and trust...	19	Experimental	—	JavaScript
85	jacklatrobe/MCP-Guardian MCP Guardian acts as a proxy service for remote MCP endpoints, and...	17	Experimental	—	Python
86	AUTHENSOR/AUTHENSOR The open-source safety stack for AI agents. Policy engine, content scanner,...	16	Experimental	—	TypeScript
87	Themxhiguy/AegisEdgeAI 🔒 Secure AI at the edge by binding user, device, and workload identities to...	14	Experimental	—	Python
88	AiAgentKarl/agent-policy-gateway-mcp-js JavaScript MCP Server — PII filtering, guardrails, GDPR/AI Act compliance for agents	14	Experimental	—	JavaScript
89	AiAgentKarl/agent-policy-gateway-mcp Compliance & guardrails for AI agents — PII filtering, audit logging,...	14	Experimental	—	Python
90	AiAgentKarl/agent-audit-trail-mcp Immutable audit logging for AI agents — hash-chained event log, integrity...	14	Experimental	—	Python
91	jagmarques/asqav-mcp MCP server for AI agent governance - policy checks, audit trails, compliance	14	Experimental	—	Python
92	JesmineT/cybersentinel-pydantic-logfire Assessment prototype built with Pydantic AI, context and state management,...	14	Experimental	—	Python
93	permission-protocol/mcp-guard MCP middleware that blocks dangerous AI agent actions using a simple YAML config	14	Experimental	—	TypeScript
94	polymons/MCP-Security-Proxy A project to test MCP voulnerabilities and defense strategies in a...	13	Experimental	2	Jupyter Notebook
95	SecAI-Hub/mcp-firewall Default-deny enterprise MCP gateway with signed policy bundles and taint tracking	13	Experimental	—	Go
96	Rizwan723/MCP-Security-Proxy 🔒 Implement a security proxy for Model Context Protocol using ensemble...	13	Experimental	—	Jupyter Notebook
97	awilmoth/mcp-firewall MCP Firewall	10	Experimental	1	Python

Comparisons in this category

gia-mcp-server and mcp-guardian (50 vs 39) gia-mcp-server and deterministic-agent-control-protocol (50 vs 39)