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.
-
agent-guardrailsgithub.com/logi-cmd/agent-guardrailsupdated this year
Checks AI-generated code changes before merge: scope, validation, risk, review evidence, and optional Verity receipts.
npm MIT ★ 28 -
Action-level governance for AI agents -- control what they DO, not what they SAY
pypi -
Deterministic CI/CD gate and native MCP server to block AI coding agents from slopsquatting, breaking architecture, and bypassing linters.
MIT -
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 -
@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 -
@availsync/mcpupdated this year
MCP server for Availsync coding-agent and scheduling guardrails.
npm MIT -
Privileged command execution for autonomous AI coding agents with arm/disarm windows and OS destabilization guardrails
MIT -
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 -
metabase-mcp-progithub.com/orlik9l/mcpsupdated this year
Agent-first Metabase MCP server with a pluggable, table-scoped query-guardrail layer.
pypi MIT -
JavaScript MCP Server — PII filtering, guardrails, GDPR/AI Act compliance for agents
npm MIT -
Multi-agent LLM research platform: parallel data agents, synthesis agents, deterministic guardrails, MCP server
MIT ★ 1 -
A semantic mistake-memory system for AI agents with MCP and in-process guardrail entrypoints.
pypi MIT -
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 -
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 -
Risk guardrails for AI trading agents. Your agent proposes a trade; your policy decides.
pypi MIT ★ 3 -
Validation gates, plan checks, and token-budget guardrails for AI coding agents.
npm MIT -
promptdefend-mcpupdated this year
Prompt Defend MCP Server - 16-Layer Guardrails for AI Agents
pypi Proprietary -
MCP server giving an AI agent a Solana spending allowance capped on-chain, with guardrails and x402 payments.
npm Apache-2.0 ★ 9 -
Local guardrails for coding agents: check what Claude Code, Codex, Grok and Antigravity do before it runs
pypi Apache-2.0 -
sentinelgithub.com/milema-gif/sentinelupdated this year
Behavioral guardrails for Claude Code — stop your agent from editing before it reads
MIT -
A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.
MIT ★ 3 -
Guarded multi-turn recruiting agent: MCP server, LangChain MCP adapters, LangGraph, conversational evals with guardrail ablation, FastAPI, Docker, CI.
MIT -
promptdefend-mcpgithub.com/promptdefend/promptdefend-mcpupdated this year
Prompt Defend MCP Server - 16-Layer Guardrails for AI Agents
npm SEE LICENSE IN LICENSE -
A Multi Agent System for planning perfect trip, using LangGraph, MCP, Supervisor, Guardrails, and Human in the loop concept.
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 -
MCP tool servers (hybrid RAG + contract rules DB) driven by a LangGraph agent, with two-layer guardrails, CI-gated retrieval evals and OpenTelemetry tracing. Dockerized, CI-tested, free to run.
MIT -
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 -
Enterprise AI agent platform: LangGraph agent, agentic RAG on PostgreSQL + pgvector, role-based tools, human-in-the-loop, guardrails, MCP server. FastAPI, 407 tests.
-
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 -
Model Context Protocol (MCP) server providing AI agents with Draw.io C4 architectural guardrails.
npm MIT -
A 3-minute AI briefing written every weekday by an AI agent, with every fact checked against its source. MCP server + Gemini agent + guardrails.
-
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 -
OmniDoc-QA-LLM-RAGgithub.com/aniketpoojari/OmniDoc-QA-LLM-RAGupdated this year
Agentic NL-to-SQL assistant using Model Context Protocol (MCP) with multi-layer guardrails and token cost tracking.
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 -
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 -
Local customer-support agent: LangGraph + MCP + LangMem + NeMo Guardrails + RAGAS, free-tier Groq/Gemini
-
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 -
JEV Gateway: PII/PHI guardrails for coding agents. Local MCP server, 0.8B inspector, and agent skills for Codex and Claude Code.
MIT ★ 1 -
Open-source CLI and MCP server for Codapult SaaS projects, with setup, plugins, database, deployment, and AI-agent architecture guardrails.
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 -
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 -
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 -
arthagithub.com/sidhvik17/arthaupdated this year
Multi-agent equity research crew (Google ADK) that writes balanced briefs and refuses financial advice by construction - deterministic prompt-injection guardrail, MCP tool server, 12 tests. Kaggle x Google Agents Capstone.
MIT ★ 2 -
Multi-agent support-ops copilot on MCP: human-in-the-loop approvals, prompt-injection guardrails, OpenTelemetry tracing and scenario evals.
MIT -
Text-to-SQL analytics agent: semantic layer, 3-layer SQL guardrails, eval harness (47 golden Qs) and MCP server. Runs offline; optional OpenAI/Ollama planner.
MIT -
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 -
AI-native architecture linter and guardrail for Go with zero-config presets and native MCP server for coding agents
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 -
A deployment layer for a guardrailed clinical conversational agent: real FHIR over MCP, PHI redaction, a hash-chained audit trail, and an evaluation harness measured on held-out data it was never tuned on.
MIT -
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 -
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 -
Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.
npm MIT -
An LLM agent that fixes git mistakes from plain-language requests, safely: sandboxed runs, auto backups, human approval for destructive steps, and hard guardrails. CLI + MCP server.
MIT -
atlas-agent-intelligence-layergithub.com/adrianofratelli-glitch/atlas-agent-intelligence-layeractive
AI agent intelligence layer in MongoDB Atlas: prompts, model config, semantic cache, guardrails and short/long-term memory stored as documents and changed live, plus an MCP tool-use loop.
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 -
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.
-
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 -
claude-code-invoice-guardgithub.com/mikko-lab/claude-code-invoice-guardupdated this year
Deterministic guardrail (refuse, don't guess) for an LLM agent on a VAT-critical invoice workflow: skill + subagent + MCP server + PreToolUse hook. Portfolio/demo plugin.
MIT -
ISO 9001:2015 / Agile V / W3C PROV-DM Quality Pipeline, Anti-Tamper HMAC Guardrails, MCP Server & Benchmark Suite for Multi-Agent Systems
MIT ★ 1