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.
-
Google Ads Transparency Center API example in Python, JavaScript and n8n: competitor ads, new-ad alerts, Google ad library. MCP-ready for AI agents.
MIT -
meok-mcp-explainabilitygithub.com/meok-ai-labs/mcp-explainabilityupdated this year
MCP server for AI explainability and transparency
npm MIT -
claude-auragithub.com/brunuff/claude-auraupdated this year
Andon board for human-AI interaction — transparency dashboard for Claude Code sessions
MIT -
meok-watermark-attest-mcpgithub.com/csoai-org/meok-watermark-attest-mcpupdated this year
EU AI Act Article 50 watermarking + transparency compliance MCP. Built for the 2 August 2026 cliff. Article 50 transparency obligations apply from 2 Aug 2026; pre-existing systems have until 2 Dec 2026. Classify Art 50 obligations (chatbot disclosure, GPAI synthetic-content marking per C2PA-2.0, deepfake disclosure, emotion/biometric transparency), generate compliant disclosure text, audit content pipelines, emit HMAC-signed attestations. By MEOK AI Labs.
pypi MIT License -
silkgithub.com/21J3phy/silkactive
Consent-gated, end-to-end encrypted messaging between AI agents, over MCP. Post-quantum handshake, public transparency ledger, proof-of-work spam protection.
mcpb Apache-2.0 ★ 1 -
opengovernmentgithub.com/provydon/opengovernmentupdated this year
A white-labelled, open-source civic transparency platform: governments publish spending, citizens file and upvote issues, with an agentic chat + MCP server. Built on Laravel 12, Inertia/Vue, laravel/ai.
MIT ★ 1 -
seif-mcpgithub.com/and2carvalho/seifupdated this year
MCP server for the SEIF Protocol — provenance signing, transparency log, and data classification tools for AI agents (Cursor, Claude Code, Claude Desktop). Thin Node wrapper around the canonical Python implementation.
npm MIT -
disclos-article-50github.com/gatisozols/disclos-article-50updated this year
MCP server that generates EU AI Act Article 50 transparency disclosures (the text you must show users) for chatbots, AI-generated content, deepfakes, emotion recognition and biometric categorisation, in all 24 EU languages, with copy-paste HTML and machin
npm MIT -
osint-mcp-servergithub.com/badchars/osint-mcp-serverupdated this year
OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.
npm MIT ★ 62 -
MCP server for CertIndex — Certificate Transparency search tools for AI assistants
pypi MIT -
switchboard-mcpgithub.com/yourname/switchboard-mcpupdated this year
Intelligent multi-provider agent routing MCP server — transparently switch between AI providers and models
pypi MIT -
stitch-mcpgithub.com/piyushcreates/stitch-mcpupdated this year
A transparent MCP server for Google Stitch. Connects AI agents directly to the official Google design API.
-
acttracegithub.com/goww7/acttraceupdated this year
EU AI Act compliance: classify AI systems by risk and generate Article 50 transparency notices. API + MCP server + Claude Code skill, for non-financial SaaS.
pypi Apache-2.0 ★ 1 -
TrustChain - decentralized trust for AI agents. Rust core, QUIC P2P, transparent proxy, MCP server, dashboard
Apache-2.0 ★ 7 -
Defygithub.com/ASIKKANI/Defyupdated this year
An MCP-powered autonomous AI trading agent that executes crypto trades via smart contracts while logging every decision on-chain for full transparency, auditability, and trustless AI–Web3 integration.
★ 1 -
A transparent MCP server that gives AI agents an operator-sanctioned place to pause, reflect, converse, or decline.
npm MIT -
linode-mcpgithub.com/piyushcreates/linode-mcpupdated this year
A transparent MCP server for Linode using the official linode_api4 Python SDK. Securely manage cloud infrastructure via AI.
-
nyc-school-explorergithub.com/jkinberg/nyc-school-explorerupdated this year
An AI-native data journalism tool for exploring NYC School Quality Report data through natural language conversation, with responsible AI guardrails and transparent methodology.
-
AI-assisted chiller troubleshooting demo powered by MongoDB Atlas, MCP tools, and an LLM agent with real-time retrieval transparency.
MIT ★ 1 -
MCP server for ReDe(ReWorks) built-in debugging: MI2 client + transparent MI shim, lets AI drive the IDE's own debug session
-
gnosys-mcpgithub.com/proticom/gnosys-mcpupdated this year
Gnosys — Persistent Memory for AI Agents and Universal Transparent Knowledge Engine. MCP server + CLI.
npm MIT -
aegisgithub.com/getaegis/aegisupdated this year
Credential isolation for AI agents. Local-first transparent proxy — your agent never sees your API keys.
npm Apache-2.0 ★ 16 -
Keyless web search for AI agents through your own SearXNG instance. One MCP tool, zero API keys, zero tracking. Engine-transparent results.
Apache-2.0 -
reportitnowgithub.com/krimler/reportitnowupdated this year
POSH Act compliance POC: state machine, audit chain, six role-bounded AI assistants, transparency dashboard with differential privacy.
-
AutomationNation Data Toolsno update data
18 data tools for AI agents: Google web search, Flights, Hotels, Shopping, News, Images, Videos, Jobs and Trends, Google Maps leads, Ads Transparency, YouTube transcripts, app reviews and AI visibility.
smithery -
recon-mcpgithub.com/nekiyRichie/recon-mcpupdated this year
MCP server exposing 15 free OSINT tools to AI agents — certificate transparency, DNS, host exposure, CVEs, RDAP, Wayback. No API keys required.
MIT -
Sourced as an MCP server for AI agents: corroboration verdicts (assess), transparency-chain verification (verify_chain), and the G1–G7 honesty suite (run_conformance).
npm MIT -
sift-mcpgithub.com/enmito/sift-mcpupdated this year
MCP server that wraps Brave Search and augments each result with a transparent quality vector for AI agents.
MIT -
🔌 Exposes By [MEOK AI Labs](https://meok.ai) | An over MCP — for AI explainability and transparency reports.
pypi MIT ★ 1 -
Video to sprite sheet converter with transparent PNGs, JSON atlases, and Unity, Unreal Paper2D, and Phaser exports. CLI, Python API, and AI agent/MCP support.
MIT -
Your AI's trust filter, owned by you. Rate any URL, filter your AI's sources, build transparent information markets. MCP server + REST API + Python SDK.
npm ★ 1 -
sherlock-mcpgithub.com/Burnsedia/sherlock-mcpupdated this year
Sherlock MCP Server: Find truth and counter propaganda through ethical OSINT. FastMCP integration for social media username searches across 400+ platforms using Model Context Protocol. Empowering investigators, journalists, and AI assistants with transparent, verifiable tools.
★ 8 -
fettlegithub.com/Deekshith-Dade/fettleupdated this year
fettle — own your Fitbit/Pixel health data: local Google Health API sync, a transparent readiness & insights engine, and a zero-cost AI coach with memory (FastAPI + Next.js + MCP + opencode)
MIT ★ 3 -
@buxapi/mcpactive
MCP server for the BuxAPI crypto payment API. Gives an AI coding assistant real tools against your wallet: create invoices, read deposits, verify webhook signatures, publish the wallet transparency page.
npm MIT -
A local MCP server for generating image assets using Google Gemini AI (Nano Banana 2 / Pro). Enable transparency and resize.
npm MIT ★ 10 -
💧 Exposes EU AI Act Article 50 watermarking and C2PA 2.1 checks over MCP — built for the 2 December 2026 transparency deadline. MIT.
pypi NOASSERTION -
A Model Context Protocol (MCP) server that enables AI agents to generate design assets using Google's Gemini models. This server provides tools for generating images and creating assets with transparent backgrounds.
-
K-Trendzgithub.com/hans1329/K-Trendzupdated this year
Fan-powered K-Pop artist support platform with on-chain transparency, bonding curve tokenomics, and AI agents that act as fans on your behalf — built on Base
★ 1 -
Universal AI Co-Producer for DAWs · Bit-transparent ITU-R BS.1770-4 telemetry, 128-band RTA & zero-latency native accessibility bridges (macOS / Logic Pro & Steinberg).
NOASSERTION -
rootedgithub.com/StephenSook/rootedupdated this year
Open-source, vendor-neutral C2PA Soft Binding Resolution server on Backblaze B2. Recovers stripped provenance for AI image, audio, and video, with a WORM transparency log and an MCP surface.
NOASSERTION -
Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin
MIT ★ 106 -
An explainable AI healthcare system that predicts diabetes risk using ML, MCP, and SHAP-based insights. It delivers transparent, clinically meaningful assessments through a modern microservices architecture, enabling healthcare professionals to make clear, data-driven decisions.
MIT -
MCP tools for AI agents: Korean music charts (Melon, Genie, Bugs, FLO, VIBE), KB부동산 apartment prices, Amazon ratings, Google Play reviews, Google Ads Transparency, Agoda hotel prices.
MIT -
MCP (Model Context Protocol) server for Caveman.PrivacyGuard — exposes PII detection/masking, session-based restore, AI-transparency notices, and prompt-injection screening as MCP tools for Claude Code, OpenCode, Cursor, and any MCP-compatible agent.
nuget MIT -
eu-ai-act-checker-mcpgithub.com/marilynceo/eu-ai-act-checker-mcpupdated this year
Classify AI systems by EU AI Act risk category, check prohibited practices (Art.5), assess high-risk designation (Annex I+III), GPAI obligations (Art. 51-56), transparency requirements (Art. 50), conformity procedures (Art. 43), and compliance deadlines.
-
AI-agent image generation: image, character, illustration and concept sets, and logo variations. PNG/WebP (optional transparency) or JPEG.
MIT ★ 1 -
logicnodesgithub.com/cmdenney/logicnodesupdated this year
Deterministic blockchain utilities for AI agents - gas estimation, outcome verification, and conditional USDC escrow on Base that settles only when an independent verifier confirms the outcome. Public track record: logicnodes.io/transparency
-
A Perplexity API MCP server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter.
go Apache-2.0 ★ 26 -
The universal MCP server for Claude Code and other MCP-compatible clients. One installation gives AI access to 10,000+ PowerShell modules and any CLI tool. You and AI collaborate in the same console with full transparency. Supports Windows, Linux, and macOS.
MIT ★ 110 -
AI-powered old-age pension assistance platform that connects citizens and block officers through secure MCP servers, OAuth 2.1 authentication, and a government pension portal. Built to simplify applications, track pension status, and support transparent officer approvals.
MIT -
ABS Zalo Agent Engine — Free, Transparent & Autonomous Zalo AI Agent Engine for Hermes, Claude Code & Codex. Dual Personal QR + Official OA, Group Administration, Lead Intel, Polls, Reactions & MCP Server.
npm MIT -
Multi-Agent-Dynamic-Matrixgithub.com/Moun7sh/Multi-Agent-Dynamic-Matrixupdated this year
MADMAX is an Enterprise AI Workforce Operating System built on NitroStack and MCP. It autonomously plans, discovers capabilities, orchestrates specialized AI agents, verifies outcomes, and delivers transparent, executive-ready business decisions.
★ 1 -
perplexity-mcp-serverstale
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter. Built with
npm Apache-2.0 -
noodle-perplexity-mcpgithub.com/fahd-noodleseed/perplexity-mcp-serverupdated this year
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, transparent reasoning, and multimodal support with file attachments (P
npm Apache-2.0 -
cybersecurity-intelligence-mcpgithub.com/apifyforge/cybersecurity-intelligence-mcpupdated this year
Cybersecurity intelligence for AI agents — search 200,000+ CVEs, check the CISA Known Exploited Vulnerabilities catalog, enumerate subdomains via Certificate Transparency, audit DNS and email security, scan internet-exposed hosts via Censys, and investigate domain registration — all through a single MCP server.
MIT ★ 1 -
KR Mycelia Memory – A native Windows 11 AI memory system powered by a Dynamic Associative Database (DAD). Persistent local memory, offline-first AI integration, MCP agent access, semantic associations, document and media processing, and transparent source-backed recall. Built in C++20.
NOASSERTION -
@iflow-mcp/cyanheads_perplexity-mcp-serverupdated this year
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter. Built with
npm Apache-2.0 -
A transparent, Markdown-backed, L0-L3 tiered hybrid memory system for AI agents with CBT safety and enterprise multi-tenancy support. Powered by MCP. 中文:为 AI Agent 打造的透明 Markdown 白盒与 L0-L3 分层混合记忆系统,兼顾 CBT 心理安全与企业级多租户支持,由 MCP 驱动。
MIT -
Check a Slovak company by IČO or name: business register, financial statements, debts to the state and insurers, VAT status and a transparent 🟢/🟠/🔴/⚪ risk verdict from public sources. Website + MCP server for Claude and other AI clients.
MIT -
LLM-nexusgithub.com/saanvijay/LLM-nexusupdated this year
A transparent HTTPS proxy between any AI client and upstream LLMs — redacts PII, compresses prompts, caches semantically similar responses, and surfaces everything in a real-time dashboard. Configurable via a single JSON file with upstream proxy chaining and MCP server integration.
MIT