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.
-
PostgreSQL schema intelligence MCP server with offline linting, migration safety, query validation for AI coding assistants.
npm BSD-2-Clause ★ 36 -
A type system, state validator, and safety firewall between AI coding assistants and physical instruments — schema-driven, MCP-native, zero hardware knowledge in the engine.
MIT ★ 1 -
fhir-factguardgithub.com/gedp/fhir-factguardupdated this year
FHIR FactGuard: Zero-Trust clinical safety layer for AI agents. Validates medication claims against FHIR patient records + RxNorm. Built for Agents Assemble Hackathon 2026.
-
🔌 Lets an MCP client check drug interactions, validate dosages, assess patient risk, and generate safety alerts. Uses evidence-based reference data. Not a substitute for clinical judgement.
npm MIT -
user-query-guardgithub.com/gowthams05/user-query-guardupdated this year
A safety gateway for validating user queries before they reach LLMs, agents, tools, or RAG pipelines.
pypi MIT -
Rivet — SDLC traceability, validation, and MCP server for safety-critical systems (ISO 26262, DO-178C, ASPICE, STPA)
npm Apache-2.0 -
An MCP server, CLI, and Claude Code hook that validate GitHub Actions workflows for correctness and supply-chain safety.
MIT -
Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.
npm MIT ★ 35 -
MCP tools for inspecting, exporting and checking Petrel project data without the Ocean SDK, with explicit safety and validation limits.
MIT ★ 5 -
A secure Model Context Protocol (MCP) server for executing commands in Windows Subsystem for Linux (WSL) with built-in safety features and validation
npm MIT -
🛡️ Rust CLI extension for Claude Code — LLM-powered command validation, SQLite context persistence & MCP tools. Two-layer safety (rules + Ollama), vector semantic search, and user-adaptive learning.
MPL-2.0 ★ 1 -
Local safety-aware MCP bridge for Autodesk Fusion with whole-task approval, recovery checkpoints, and geometry validation.
Apache-2.0 -
@fairquery/agent-trust-mcpactive
Fairquery Agent Trust & Data Safety MCP server: PII/secret redaction, email validation, sanctions screening, dependency checks and a local MCP server pre-check for AI agents. Free local tools + optional paid Apify-backed deep tools.
npm MIT -
MCP server that lets AI agents create, edit, validate, and preview Microsoft Word report layouts for Microsoft Dynamics 365 Business Central - 23 deterministic, typed tools over stdio, with validate-before-save write safety and an offline mock PDF preview.
nuget MIT -
Permission-aware MCP server and agent harness with role-scoped tools, whole-plan validation, deterministic safety evals, and a React playground.
MIT -
mcp-clickhousegithub.com/TopWent/mcp-clickhouseupdated this year
Model Context Protocol server exposing ClickHouse to LLM clients over stdio. Read-only by default, comment-aware SQL safety validator, five tools, distroless image.
MIT -
craft-unitygithub.com/SkyWalker2506/craft-unityupdated this year
CRAFT — Safe AI execution engine for Unity. Transaction safety, rollback, validation, + new 0.2 Inspect (screenshot, profiler, console) and ImportSettings (texture/model) ops on top of Unity MCP.
MIT -
Safety-first MCP server for AI-assisted Google Drive organization with least-privilege OAuth, deterministic validation, human approval gates, dry runs, and audit logging.
-
snapgraph3dgithub.com/scifiss/snapgraph3dupdated this year
Constraint-guided 3D scene assembly agent with typed scene graphs, connector validation, repair/rollback safety, Unity export, and MCP tooling.
Apache-2.0 -
fhir-mcp-suitegithub.com/pcmedsinge/fhir-mcp-suiteupdated this year
Three MCP servers for clinical AI: FHIR R4 query + US Core validation, SNOMED/LOINC/ICD terminology, and drug safety reasoning via FDA labeling — composable, production-ready, Apache-2.0.
pypi NOASSERTION ★ 1 -
Code-aware MCP server with AST parsing for Go, TS, JS, Python, C/C++, HTML, Vue, React. Tree-sitter + LSP integration enables syntax validation, symbol navigation, refactoring safety. Performance: LRU cache, xxHash (453ns), 229x faster regex caching. Tailwind-aware, concurrent-safe editing.
MIT ★ 4 -
agentic-deep-auditgithub.com/th3vib3coder/agentic-deep-auditupdated this year
Evidence-first repository audit engine for local & GitHub projects. Python CLI with safety model, provenance tracking, supply-chain/license/risk analysis, MCP handoff, schema validation and portable audit artifacts.
-
txt-to-sqlgithub.com/pavani-aiml-space/txt-to-sqlupdated this year
A natural-language-to-SQL agent over Postgres/Supabase that translates plain-English questions into validated SQL and self-corrects on failure, with a rule-based fallback, safety policy layer, benchmark suite, and MCP server.
-
oswaldgithub.com/austinAbraham/oswaldupdated this year
Oswald the Analytical Octopus — a runtime-agnostic, MCP-native, context-rot-resistant workflow layer for analytical-engineering AI agents. Eight tentacles, durable .oswald artifacts, safety policy engine, dbt build/test/validate. MIT.
npm MIT -
MCP server and Unreal Engine 5.9 editor plugin that let AI agents inspect, plan, build and validate Unreal worlds, with multi-agent editor leases and native safety checks.
MIT ★ 13 -
Open Delta DVP PLC engineering IDE (WinUI 3 / .NET 8) with a first-class MCP server for AI agents. Semantic ladder IR, capability-validated models, Modbus RTU/ASCII, safety-tokened writes, 129 tests.
MIT -
Dual MCP servers exposing Solid Edge's COM API: an execution server with a permission-onion safety layer and dry-run validation, plus a live event-stream server. Drive CAD from any MCP client.
MIT ★ 4 -
Pay-per-call verification for AI agents: on-chain arbitrage profitability, token safety, swap routing, quote validation, and trade sizing powered by x402 USDC micropayments.
npm Apache-2.0 -
sqlite-explorer-fastmcp-mcp-servergithub.com/hannesrudolph/sqlite-explorer-fastmcp-mcp-serverstale
An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.
★ 108 -
Instructing rehabilitation robots with language models over the Model Context Protocol. A robot-agnostic core with a deterministic safety validator between the model and the hardware, demonstrated on a Novint Falcon under ROS 2. ETH Zurich SMS Lab semester project.
MIT ★ 1 -
1trippulse-mcp-servergithub.com/gkcogz/onetrip-betaupdated this year
1trip PULSE — The #1 travel planning MCP server. 21 tools, 5 resources, 6 prompts. Live flights, hotels, weather, currency, visa, safety (50+ countries), trip skeletons, validation, insights, packing, local tips, personas. 120+ city cost index. Works with
npm MIT -
Valet - MCP servers that let an AI agent (Claude Code) trade for real: Interactive Brokers (quotes, positions, market/limit/stop/trailing/bracket, FRACTIONAL buys by the dollar) + crypto spot via CCXT with exchange-native stop orders. Hexagonal architecture, paper-first, fail-closed safety guards on every order. Live-validated.
MIT ★ 15 -
lemmagithub.com/0210shivam/lemmaupdated this year
MCP-native post-generation validation layer for LLM outputs
-
@ruso-0/tokenguardgithub.com/ruso-0/tokenguardupdated this year
MCP plugin for Claude Code — 3 router tools with invisible middleware for token-optimized code navigation, compression, and safety. Lite mode (instant) or Pro mode (semantic search).
npm MIT -
mcp-hallucination-suitegithub.com/steveswain14/mcp-hallucination-suiteupdated this year
A unified suite of MCP suppressors that prevent hallucinations, enforce grounding, and stabilise agent behaviour.
NOASSERTION -
t1-t2-protocolgithub.com/Fauxetine/t1-t2-protocolupdated this year
MCP server for heterogeneous AI validation — T1 structured reasoning, T2 cross-model evaluation, and deterministic checksum. Python stdlib-only.
pypi Apache-2.0 -
mcp-json-suppressorgithub.com/steveswain14/mcp-json-suppressorupdated this year
A standalone MCP suppressor that sanitises, validates, and stabilises JSON outputs to prevent malformed or hallucinated structures.
NOASSERTION -
@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 -
antrieb-mcp-servergithub.com/jade-pico/antrieb-mcp-serverupdated this year
Real VMs for your LLM. Provision, execute, validate. In seconds. LLM4Ops.
Apache-2.0 ★ 14 -
MCP (Model Context Protocol) Server for TypeScript Type Guard Generation - Generate runtime validation functions from TypeScript types
npm MIT -
oracle-h-mcpgithub.com/tponscr-debug/oracle-h-mcpupdated this year
MCP Server for ORACLE-H — Human-on-the-Loop validation for autonomous AI agents
npm MIT -
@sgraal/mcpgithub.com/sgraal-ai/coreupdated this year
AI agent memory governance MCP server — preflight validation before every action. Works with Claude Desktop, LangGraph, and any MCP-compatible client.
npm Apache-2.0 -
Blankstate MCP Server — protocol sensing, action validation, and Programmatic Dive tools for Cursor, Claude, and other MCP hosts
npm MIT -
A standalone MCP suppressor that filters, stabilises, and sanitises tool responses to prevent hallucinated or unsafe output.
NOASSERTION -
MCP service to convert TypeScript types and interfaces to Zod schemas with automatic dependency tracking and cross-file reference support
npm MIT -
.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.
nuget Apache-2.0 ★ 11 -
mcp-server-stage0-authorizationgithub.com/Starlight143/mcp-server-stage0-authorizationupdated this year
MCP server demonstrating server-side authorization with Stage0 runtime policy validation
MIT -
Safe file editing for AI agents: back up, validate, roll back on failure. Zero-dependency MCP server.
MIT ★ 1 -
microsoft-todo-safe-mcpgithub.com/Saenai/microsoft-todo-safe-mcpupdated this year
Local-first Microsoft To Do MCP server with safe AI plan validation, preview, backup, confirmation, and audit logs.
-
MCP server providing secure file operations with prompt injection detection, API key validation, and audit logging
-
mcp-grounding-enforcergithub.com/steveswain14/mcp-grounding-enforcerupdated this year
A standalone MCP suppressor that enforces grounding by validating references, rejecting unsupported claims, and stabilising model outputs.
NOASSERTION -
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 -
MCP server for AI agent security -- input validation, prompt injection detection, PII redaction, policy enforcement, rate limiting, and audit logging
cargo MIT ★ 1 -
veriethiccore-mcpgithub.com/fatdinhero/veriethiccore-mcpupdated this year
VeriEthicCore — EU AI Act + Halal Compliance MCP Server. The world's first MCP combining EU AI Act risk scanning with Islamic Sharia ethics validation.
MIT -
A modular registry for trustworthy, evidence-based genomic analysis powered by Model Context Protocols (MCPs). Bridging AI and clinical genomics with traceable, validated data retrieval.
MIT ★ 1 -
ha-gatekeepergithub.com/antnewman/ha-gatekeeperupdated this year
A reliability-first MCP server for Home Assistant implementing the LLM-as-untrusted-advisor architecture with four-tier policy engine, hash-chained audit logging, and fuzzy entity validation.
MIT -
claude-india-dpigithub.com/romichandra/claude-india-dpiupdated this year
An enterprise-grade AI gateway framework designed to safely and deterministically scale frontier language models across India's Digital Public Infrastructure (DPI) registries via MCP, Pydantic type-guards, and SymPy validation.
-
MCP server that gives AI agents a compact map of a database schema, finds join paths between tables, and validates SQL through an AST-based read-only guard (sqlglot).
MIT -
rocket-toolsgithub.com/benajaero/rocket-toolsupdated this year
80 validated aerospace-engineering tools for Python, the CLI, and MCP agents: structures, aerodynamics, compressible flow, propulsion, orbital mechanics, ascent and recovery, optimization, and reliability. Every result is traceable to a published reference.
pypi NOASSERTION ★ 1 -
@toolated/coherence-mcpgithub.com/toolate28/coherence-mcpupdated this year
MCP server for coherence validation across AI systems. TriWeavon Formal Executable Mapping v0.4 — WAVE scoring, ATOM trail provenance, SRAC correction bursts, cross-platform translation (Claude/Grok/Gemini/Llama), and industry connectors. Conservation law
npm MIT