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.
-
MCP Server for Swiss Federal Food Safety and Veterinary Office (BLV) open data — no auth required
pypi MIT -
vehicle-safety-mcpgithub.com/basit-khan-abdul/vehicle-safety-mcpupdated this year
MCP server connecting Claude to NHTSA vehicle safety data — VIN decoding, recalls, NCAP ratings, and complaints. No API key required.
MIT -
🔌 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 -
MCP server exposing FDA drug-safety data (labels, FAERS adverse events, recalls, label-documented interactions) with structured outputs, plus a LangGraph agent that discovers and uses its tools. Works with Claude Desktop, Cursor and any MCP client.
MIT -
aviation-safety-risk-mcpgithub.com/apifyforge/aviation-safety-risk-mcpupdated this year
Aviation safety intelligence for AI agents — this MCP server queries 8 live government data sources in parallel and returns a composite Aviation Safety Score (0-100) covering airline safety defects, airworthiness directives, route weather risk, sanctions exposure, and maintenance compliance.
MIT -
influencer-brand-safety-intelligence-mcpgithub.com/apifyforge/influencer-brand-safety-intelligence-mcpupdated this year
Influencer brand safety screening for AI agents and brand teams — this MCP server delivers automated creator vetting, controversy risk analysis, audience authenticity scoring, and sanctions screening through 8 callable tools that orchestrate 9 parallel data sources.
MIT ★ 1 -
Free, proof-only App Store & Google Play compliance checker: catch App Store rejections, privacy manifest, Data Safety & policy issues in Expo/React Native apps. CLI, MCP server, AI agent skill & GitHub Action.
MIT -
coach-kernelgithub.com/LeesungDang/coach-kernelupdated this year
Deterministic safety kernel for AI-agent training plans, with MCP data boundaries, Claude Agent SDK integration, replay evals, and fuzzing.
MIT -
Pharmaceutical R&D Pipeline Intelligence MCP Server — Clinical trials, FDA/EMA approvals, safety data. Questions? Start here!
MIT ★ 5 -
deskclawgithub.com/Lelevinson/deskclawupdated this year
An AI customer-service agent that runs a real (mock) shop over WhatsApp — with hard safety rails. Skills → typed MCP tools → shared data, on OpenClaw.
MIT -
MCP server for FDA drug information lookup and safety data. Provides access to FDA drug labels, adverse events, and regulatory information through the openFDA API.
npm MIT -
AI copilot that answers plain-English questions about ERP sales data. Read-only by design: LangGraph agent, MCP tools, 4-layer safety. FastAPI + SQLite + free OpenRouter models.
-
Text2SQL data-analysis agent: three handwritten LangGraph orchestrations (deterministic pipeline / autonomous ReAct loop / Supervisor multi-agent with LLM-as-Judge), 4-layer SQL safety, MCP server+client, human-in-the-loop write path with transactional dry-run. 60-case gold benchmark.
MIT -
schwab-mcpgithub.com/gray584321/schwab-mcpupdated this year
Safety-first MCP server for Charles Schwab trading (market data, accounts, and gated order placement).
MIT -
MCP server + skills for AI agents to work directly with Power BI — DAX query with data-safety policy, PBIR report templates, end-to-end analysis pipeline (Claude Code / Codex / Antigravity)
NOASSERTION ★ 3 -
AI-Data-Access-Gatewaygithub.com/HanZephyr/AI-Data-Access-Gatewayupdated this year
An open-source secure data access gateway for AI agents. It provides database safety access services to AI agents through the MCP protocol. 一个面向 AI Agent 的开源安全数据访问网关,通过 MCP 协议为 AI Agent 提供数据库安全访问服务。
Apache-2.0 ★ 5 -
MCP server: pay-per-call market data + agent tools via x402 (USDC on Base). Web page reader, email verification, token safety, sentiment, prediction markets, regime forecasts, quotes, macro.
npm MIT -
Honest Nankai Trough earthquake hazard + building-safety MCP — official Japan data only, no verdicts.
npm MIT -
MCP tools for inspecting, exporting and checking Petrel project data without the Ocean SDK, with explicit safety and validation limits.
MIT ★ 5 -
mcp-data-analystgithub.com/flashgari/mcp-data-analystupdated this year
Natural-language data analyst: Claude answers questions by calling tools over a real MCP server (including a real subprocess/stdio test), with a read-only SQL safety guard and a FastAPI + Chart.js dashboard. 57 tests against real infrastructure.
MIT -
guardian-mcp-v2github.com/azadDsync/guardian-mcp-v2updated this year
MCP system for pedestrian safety assessment using real-time data from Google Maps, OpenWeather, YOLOv8, and Moondream2 Vision AI.
★ 1 -
CyberWareX MCP servers: pay-per-call x402 tools for AI agents (USDC on Base, no API key). Token safety/honeypot oracle, EVM chain data, web access (markdown/screenshot/PDF), wallet safety (tx sim, signature decode, address risk, ABI, URL phishing), speech-to-text.
MIT -
mcpgithub.com/glimind/mcpactive
Glimind MCP server: live reliability, agent-readiness and safety data for every public MCP server.
MIT -
Conversational MCP server for pharmacovigilance research using public openFDA safety, label, and recall data.
pypi MIT -
senmcpgithub.com/AlKountiyou/senmcpupdated this year
An open-source Senegal civic MCP stack: MCP servers for public data and citizen services, with a LangChain/LangGraph agent, provenance, and safety-by-design.
MIT -
url-ai-mcpgithub.com/csoai-org/url-ai-mcpupdated this year
Url Ai MCP server. Tools: parse url, shorten url data, check url safety. Built by MEOK AI Labs.
npm MIT -
solana-mcp-servergithub.com/aiagentkarl/solana-mcp-serverupdated this year
MCP server giving AI agents access to Solana blockchain data — wallets, token prices, DeFi yields, safety checks
pypi MIT -
Sourced, granular data on living in Italy, by comune, province and region: housing prices and rents (OMI), demographics, foreign residents, climate, healthcare, safety and tax regimes. Every value carries its source, reference year and extraction date. Mirror of expatliving.it/data, also served as a REST API (OpenAPI) and an MCP server.
NOASSERTION -
Unified MCP server and 13-tool suite for official European Union and Nordic open data (TED EU tenders, PRH Finnish + Brreg Norwegian company events, GLEIF LEI & ownership, EU VAT rates (TEDB), EU Safety Gate product alerts, EU sanctions, VIES VAT, ECB FX
npm MIT -
Remote MCP server for Kamchatka travel: local operator tours with real prices, transfers, lodging, trip planner, volcano/weather/safety data
MIT -
mongo-scout-mcpgithub.com/bluwork/mongo-scout-mcpupdated this year
Scout your MongoDB databases with AI - A production-ready MCP server with safety features, live monitoring, and data quality tools
npm Apache-2.0 -
MCP server giving AI agents BNB Chain, opBNB and Greenfield tools for chain data, token safety, swaps and storage.
npm NOASSERTION ★ 35 -
🔌 Exposes Healthcare FHIR compliance over MCP — patient data handling, HIPAA/GDPR dual compliance, clinical decision support safety. MIT.
npm MIT -
Safety-first agentic Oracle DBA skills for Claude Code: 24 tier-gated executable domains (RMAN, Data Guard, RAC, perf, security…) fused with Oracle's official knowledge base, native SQLcl-MCP + a custom guarded host-ops MCP server.
NOASSERTION ★ 7 -
🔌 Exposes Agricultural robotics compliance over MCP — HSE PUWER, farm safety, autonomous vehicle standards, crop data privacy. MIT.
npm MIT -
Clinical question-answering service over guidelines and FHIR patient data, with dose verification, safety guardrails, an MCP server and an evaluation gate in CI.
MIT -
Chinese company data and screening reports: V3 calls 0.011 USDC; HTTP x402 Standard 0.29, Enhanced 0.59, QCC qualifications JSON 0.03. MCP data tools and legacy packages retained; scoped results, not a safety verdict.
NOASSERTION -
Project-Heimdallgithub.com/AnubhavMadhav/Project-Heimdallupdated this year
A high-security Model Context Protocol (MCP) server for PostgreSQL. Acts as a read-only gatekeeper for LLMs by using AST parsing to strictly enforce safety and prevent data mutation.
MIT -
snowsure-mcpgithub.com/mikeslone/snowsure-mcpupdated this year
Hosted MCP server for live ski & snow data — 14-day forecasts, powder rankings, resort guides, avalanche/road safety, and grounded Q&A across 500+ resorts. No install, no auth.
pypi MIT ★ 1 -
An MCP server that lets an AI assistant read and write Moodle in plain language. Reads, writes, and safety limits are kept separate, so nothing touches live data by accident.
MIT ★ 2 -
High-performance MongoDB Model Context Protocol (MCP) server optimized for LLMs - enables AI agents to safely and efficiently query and manipulate MongoDB data with type safety, schema validation, and controlled access patterns
npm MIT -
Safety-gated MCP server for industrial IoT — read sensor data, control motors with 3-layer write protection and audit trail. FastMCP, deterministic mock adapter, runs in CI with no infra.
MIT -
MCP server that connects Redash to Claude AI — query data, manage dashboards, and run SQL with natural language, with built-in SQL safety guards.
npm MIT -
spice_baegithub.com/fabiantoh98/spice_baeupdated this year
AI-powered spice advisor with 88+ spices, nutritional data (USDA), health benefits (NCCIH), and safety info -- built with Gradio, LlamaIndex, Neo4j, and Claude. Exposes tools via MCP for AI agent integration. Built for the MCP 1st Birthday Hackathon.
-
litmuz-agentgithub.com/ombharatiya/litmuz-agentupdated this year
Claim-level verification for life-sciences research agents: honest, auditable, per-claim traffic-light verdicts against the primary literature and genomic reference data. MCP-native, deterministic safety gates.
MIT ★ 1 -
MCP server for Claude that generates mountain bike and road cycling routes (loops, point-to-point, via points) on real OpenStreetMap data and saves them as GPX with elevation and safety warnings.
mcpb MIT -
ramzinex-mcpgithub.com/dwin-gharibi/ramzinex-mcpupdated this year
Self-hostable Model Context Protocol (MCP) server for the Ramzinex (رمزینکس) cryptocurrency exchange. Provides secure access to market data, balances, orders, withdrawals, and API-key management with configurable safety guardrails, multi-account support, and Docker/Kubernetes deployment assets.
NOASSERTION -
This MCP server extracts key-value pairs from arbitrary, noisy, or unstructured text using LLMs (GPT-4.1-mini) and pydantic-ai. It keeps type safety and supports multiple output formats (JSON, YAML, TOML). The server is robust to any input and always attempts to structure data as much as possible.
GPL-3.0 ★ 1 -
@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 (Node/TypeScript) giving AI assistants 153 tools for Yandex marketing: Direct ads, Metrika analytics, Wordstat keyword data, and Webmaster SEO. Self-configuring OAuth returns a clickable auth link and saves the token with no restart. Works with Claude Code, Cursor and other MCP clients; read-only and confirm safety modes.
MIT ★ 3 -
newrelic-mcpgithub.com/karldane/newrelic-mcpno update data
A Go-native MCP (Model Context Protocol) server for the New Relic observability platform, providing comprehensive access to APM, infrastructure, logs, traces, alerts, dashboards, synthetics, workflows, notifications, service levels, tags, entities, and workloads — all through a single GraphQL endpoint. Overview 55 registered MCP tools covering the full NerdGraph API surface Safety-first design: every tool carries EnforcerProfile metadata (risk, impact, resource cost, PII flag, idempotency) for automated policy enforcement via MCP Bridge Write protection: all mutation tools gated behind a -write-enabled flag; disabled by default Multi-region: US and EU data center support (NEWRELIC_REGION=us|eu)
smithery -
Stop coding agents from silently rewriting protected files: a PreToolUse guard for Claude Code and Codex, exact raw-byte edits over MCP, and verifiable receipts.
npm MIT -
agentgategithub.com/monteslu/agentgateupdated this year
API gateway for AI agents to access your personal data with human-in-the-loop write approval.
★ 46 -
Read-only MCP server over the Toronto open data warehouse: curated tools plus sqlglot-checked SQL, a least-privilege role and read-only transactions, tested end to end over MCP
MIT -
소방청 공공데이터(화재·구급·소방시설) + 법제처 소방 법령·판례 MCP 서버 — 소방관계자 실무용
npm MIT -
BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).
npm MIT -
mcp-152fz-anonymizergithub.com/Pioneer113/mcp-152fz-anonymizerupdated this year
Автоматическое обезличивание персональных данных (ПД) по 152-ФЗ. Готовый MCP-сервер и API для безопасной работы ИИ-агентов, n8n и LLM.
MIT ★ 5 -
Documented AI coding agent failures — severity-scored, source-verified, CC BY 4.0. Callable over MCP.
NOASSERTION ★ 1 -
mcp-servergithub.com/fidensa/mcp-serverupdated this year
Gives your AI agent structured access to Fidensa certification data.
npm -
piiegithub.com/janvis11/piieupdated this year
a privacy layer for your ai applications, prevent data leakage
★ 1