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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
@guardrail-ai/mcpgithub.com/manavarya09/guardrailupdated this year
Model Context Protocol (MCP) server for Guardrail — use as a Claude Code plugin
npm MIT -
MCP server providing deterministic guardrails for AI-generated test automation
npm MIT -
MCP server for Input/output policy validation
ISC -
guardrail-ai-mcpgithub.com/saifsysim/guardrail-mvpupdated this year
Guardrail AI — MCP server for Claude Desktop. Score AI responses for hallucinations, safety, and confidence. Zero setup.
npm MIT -
Your company's AI rules in every AI tool: one reviewed policy file served to Claude, ChatGPT and Codex while plans are made, plus open security skills and Claude Code hooks. No telemetry.
MIT ★ 2 -
@purplesquirrel/guardrails-mcp-servergithub.com/purplesquirrelmedia/guardrails-mcp-serverupdated this year
AI Agent Guardrails MCP Server - Security layer for Claude Code and AI agents
npm MIT -
guardrails-mcpgithub.com/turbot/guardrails-mcpupdated this year
Enable AI assistants to explore and query your Turbot Guardrails data!
npm Apache-2.0 ★ 4 -
An MCP guardrail that enforces architecture conventions while AI writes code.
MIT -
sentinel-aigithub.com/MaxwellCalkin/sentinel-aiupdated this year
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript SDKs. MCP proxy. Claude Code hooks.
Apache-2.0 ★ 27 -
promptdefend-mcpupdated this year
Prompt Defend MCP Server - 16-Layer Guardrails for AI Agents
pypi Proprietary -
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP security gateway + Claude Code/Cursor guardrails. Rust, Apache-2.0.
Apache-2.0 -
Local MCP server and CLI for learned AI guardrails, memory, skills, and agent config injection
pypi Source Available — free for personal use, commercial/government use requires wri -
pitbridgegithub.com/ToolstackVault/pitbridgeupdated this year
Local-first, guardrailed MCP bridge for NinjaTrader 8. Hard risk limits your AI agent cannot bypass; guardrails enforced outside the model, runs on your machine.
pypi Apache-2.0 ★ 1 -
promptdefend-mcpgithub.com/promptdefend/promptdefend-mcpupdated this year
Prompt Defend MCP Server - 16-Layer Guardrails for AI Agents
npm SEE LICENSE IN LICENSE -
A semantic mistake-memory system for AI agents with MCP and in-process guardrail entrypoints.
pypi MIT -
Privileged command execution for autonomous AI coding agents with arm/disarm windows and OS destabilization guardrails
MIT -
JavaScript MCP Server — PII filtering, guardrails, GDPR/AI Act compliance for agents
npm MIT -
mcp-server-sentinelseedgithub.com/sentinel-seed/mcp-server-sentinelseedupdated this year
MCP server for Sentinel AI safety seeds - add alignment guardrails to any AI agent
npm MIT -
Risk guardrails for AI trading agents. Your agent proposes a trade; your policy decides.
pypi MIT ★ 3 -
Tailored resumes from one fact library: page-target builds, fact guardrails, shortlist-ai scoring, CLI + MCP server
MIT -
deadpushgithub.com/harris-ahmad/deadpushupdated this year
Guardrails for the vibe coding era — real-time AI agent guardian with MCP write interception, git hooks, and quarantine
pypi MIT -
agent-policy-gateway-mcpgithub.com/AiAgentKarl/agent-policy-gateway-mcpupdated this year
Compliance & guardrails for AI agents — PII filtering, audit logging, GDPR/AI Act checks, kill switch
pypi MIT -
Validation gates, plan checks, and token-budget guardrails for AI coding agents.
npm MIT -
comcast-ai-demogithub.com/jtrobman/comcast-ai-demoupdated this year
AI support operations demo using RAG, MCP tools, policy guardrails, evals, and live OpenAI generation for Comcast Business-style workflows.
-
AI-powered healthcare front-desk agent built with FastAPI, Groq, and MCP, featuring deterministic safety guardrails, patient-message triage, and an evaluation harness for messages.
-
MCP server giving an AI agent a Solana spending allowance capped on-chain, with guardrails and x402 payments.
npm Apache-2.0 ★ 9 -
A 3-minute AI briefing written every weekday by an AI agent, with every fact checked against its source. MCP server + Gemini agent + guardrails.
-
Model Context Protocol (MCP) server providing AI agents with Draw.io C4 architectural guardrails.
npm MIT -
repo-medicgithub.com/mecemis/repo-medicupdated this year
AI remediation assistant for repositories with logs/traces intake, RAG, guardrails, verification, MCP, and controlled draft PR workflows.
Apache-2.0 -
@rangerchaz/aimemgithub.com/rangerchaz/aimemupdated this year
Local memory and guardrails for AI coding assistants. Your AI gets more opinionated as your codebase gets crappier.
npm MIT -
Enterprise AI agent platform: LangGraph agent, agentic RAG on PostgreSQL + pgvector, role-based tools, human-in-the-loop, guardrails, MCP server. FastAPI, 407 tests.
-
Constitutional-AI safety guardrails for any LLM — MCP server (npm: @creedspace/mcp-server, registry: io.github.Creed-Space/creedspace-mcp-server).
npm MIT -
icme-preflight-mcpgithub.com/icme-lab/icme-preflight-mcpupdated this year
MCP server for ICME Preflight — cryptographic guardrails for AI agents. Formal verification + ZK proofs, pay per request via x402 or card.
npm MIT -
agentguardgithub.com/glaborie/agentguardupdated this year
Production-grade QA layer for agentic AI - guardrails, RAG evaluation, MCP server, and drift monitoring in one self-hosted stack.
Apache-2.0 ★ 1 -
ace-packgithub.com/alex-boom/ace-packupdated this year
Local AgentOps for AI coding agents: durable memory, guardrails, and quality gates for vibe coding in real repositories.
npm MIT -
AI-native architecture linter and guardrail for Go with zero-config presets and native MCP server for coding agents
MIT -
Valta-MCPgithub.com/Valta-hq/Valta-MCPupdated this year
Financial guardrails for AI agents — pre-call spend gates and a cryptographically hash-chained audit trail. Stops an agent before it overspends, not after.
MIT ★ 1 -
Open-source CLI and MCP server for Codapult SaaS projects, with setup, plugins, database, deployment, and AI-agent architecture guardrails.
npm MIT -
A database guardrail proxy: blocks destructive SQL by real blast-radius, not just keyword shape. Freeze mode, tamper-evident audit, MCP-native for AI agents.
NOASSERTION -
speclockgithub.com/sgroy10/speclockupdated this year
Action guardrails for AI coding agents — native Claude Code enforcement, MCP integrations, and Git/CI checks.
npm MIT ★ 26 -
repo-seatbeltgithub.com/berkcangumusisik/repo-seatbeltupdated this year
A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.
npm MIT ★ 8 -
Bilingual (EN/ES) customer support agent for a home appliance store: Pydantic AI, BM25 RAG with citations, tool calling, guardrails, FastAPI + Gradio, MCP and promptfoo evals.
MIT -
Zero-dependency deterministic linter, guardrail & conservative repair engine for Mermaid diagrams in Markdown & CI/CD. Built-in MCP server for AI agents.
MIT ★ 1 -
zeroH™ Deterministic Code, Math, Claim & JSON Guardrail for AI Agents — Standalone SKILL.md on Agensi.io + MCP Server (Python 3 Stdlib)
NOASSERTION -
anchord-mcpgithub.com/nolenation04/anchord-mcpupdated this year
Hosted MCP server for identity resolution and write guardrails for AI agents. Read-only proxy to the Anchord API.
npm MIT -
Hallwright: Deterministic pre-commit guardrail, living project memory, and subagent orchestration for Claude Code, Cursor, Copilot, Antigravity, and AI coding assistants.
MIT ★ 1 -
nagi-ledgergithub.com/namakoo-dev/nagi-ledgerupdated this year
An audit ledger and guardrail toolkit for autonomous AI coding agents - MCP server + Claude Code hooks that record every dispatch, block known dead ends, and stop the agent from quitting early
MIT -
@altirs/mcp-serveractive
MCP server for Altirs — AI guardrails (content safety, PII, prompt injection, hallucination) as tools for Claude Code, Claude Desktop, Cursor, and any MCP client
npm MIT -
The brakes for agentic commerce: a guardrail gateway (caps, human approval, hash-chained ledger) between any AI agent and a PayPal seller's account. MCP server + 4 agents. PayPal AI Hackathon 2026.
MIT -
Database guardrail wire proxy, virtual schema masking & dry-run token manager for AI agents with 1-click Slack and Microsoft Teams approval feeds.
npm MIT ★ 1 -
mcp-smb-productsgithub.com/thinkneo-ai/mcp-smb-productsupdated this year
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
MIT ★ 1 -
Rule-based guardrails for AI-written reports: Python fills the numbers, checks each sentence, and keeps replayable receipts. Library, CLI & MCP.
MIT -
Whiskers — Zero-Trust MCP Control Plane for Docker & Kubernetes. Tactile observability, mTLS mesh, blast-radius guardrails, and human-in-the-loop approvals for AI agents.
oci Apache-2.0 ★ 3 -
Secure MCP server that lets AI assistants answer business questions from a data warehouse: semantic layer, 2-layer SQL guardrails, audit log, evals
-
Guardrails for AI coding agents: a project map, negative invariants, and checks they cannot talk their way around. Claude Code plugin, MCP server, pre-registered benchmarks.
MIT -
An open-source, local-first Model Context Protocol (MCP) server for **AI Search Crawler Governance, Brand Safety Guardrails, Canonical Integrity, and IndexNow Notifications
pypi MIT -
The Zero-Trust Safety & Settlement Rail for Autonomous AI Agents. Sub-10ms deterministic guardrails, key leak defense, and cryptographic Proof-of-Safety attestations via x402 on Base ($0.002).
npm MIT ★ 3 -
Guardrino by HisnLabs: the AI guardrail for Arabic, its dialects, Arabizi and English. Stops prompt injection and jailbreaks, masks Gulf personal data. OpenAI-compatible proxy, LiteLLM plugin, MCP security proxy. Built in Dubai.
Apache-2.0 ★ 1 -
An IT helpdesk AI agent with a guardrailed tool layer: 17 typed tools behind one chokepoint, human approval bound to the exact arguments, and 224 tests. Django, Celery, MCP.
-
kubeleashgithub.com/kubeleash/kubeleashupdated this year
Guardrails for AI agents on your cluster: a local, policy-gated Kubernetes MCP server with RBAC-style, context-scoped access control. Point it at an over-privileged kubeconfig — it still can't nuke prod.
go Apache-2.0 ★ 1