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.
-
Self-hosted telemetry guardian: ingests browser-console activity, scores it with a language model for insider-threat and data-exfiltration signals, and persists sessions, events and risk assessments in MongoDB via an MCP server. Experimental, not production ready.
Apache-2.0 -
SnapAPI-AI-Ready-Scrapergithub.com/Mulliner11/SnapAPI-AI-Ready-Scraperupdated this year
AI-Ready Web Scraper & Data Pipeline: Turns any URL into clean Markdown/JSON for LLMs & RAG. Built-in MCP server.
-
Seed-to-scale LLM synthetic data engine with auto-detected templates, schema validation & quality-diversity optimization. CLI + MCP ready.
MIT ★ 1 -
Composable rule engine for LLM data quality validation with IQR/Z-score anomaly detection & auto-fix pipeline. CLI + MCP ready.
MIT -
Turn your TeslaMate data into LLM-ready insights & shareable cards — declarative YAML 'plays' (read-only SQL + compute + image prompts) for ChatGPT Actions / Coze / MCP. Java 21 + Spring Boot, AGPL-3.0.
AGPL-3.0 ★ 1 -
klaketgithub.com/huseyinstif/klaketupdated this year
Turn any video into LLM-ready data - transcripts, speaker labels, scenes, subtitles and on-screen text. Self-hostable, keyless, MCP-ready.
npm AGPL-3.0 ★ 3 -
MCP server exposing your own Garmin Connect data (sleep, HRV, readiness, activities, calories, weight) as 11 read-only tools for LLMs. Built on garth-ng, runs locally over stdio.
MIT ★ 3 -
AgentReady (T6 CLI edition) — audit a public storefront for AI shopping-agent readiness from CI: UCP profile, live MCP endpoint, llms.txt, robots AI policy, Product structured data, sitemap, platform, HTTPS/canonical.
pypi MIT -
Apify Actor: Clutch.co Agency API - B2B company data, directory listings, full agency profiles and unlimited verified client reviews from Clutch.co, as structured JSON plus LLM-ready markdown. Three modes, MCP-ready, no vendor.
-
Open-source GEO & SEO readiness probe for AI crawler access, llms.txt, structured data, sitemaps, and performance.
oci MIT -
AgentReady REST API and Docker deployment for AI agent readiness scanning. Scan websites, APIs, ecommerce stores, marketplaces, MCP servers and agent services for agentic-web compatibility, discoverability, OpenAPI, llms.txt, structured data, security and AI crawler readiness. Easy to self-host.
Apache-2.0 -
Production-grade 22-level on-page + AI-search (RAG/LLM) SEO auditor with 14 dev-ready deliverables, CLI + MCP server — real measured data, no mocks. Node.js + Puppeteer + Express.
MIT ★ 1 -
io.github.Cal-Dev-Tech/perpage-mcp-serverno update data
Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.
npm -
A local MCP server that lets an LLM analyst interrogate Quebec's SEAO public-procurement open data in plain language. A small pipeline downloads the raw OCDS feed, filters it, and normalizes it into a query-ready SQLite database.
MIT ★ 1 -
oura-mcpupdated this year
Model Context Protocol (MCP) server for Oura Ring API - provides LLMs with access to sleep, activity, readiness, and health data
pypi MIT -
A comprehensive, production-ready research server (MCP). Provide your LLM clients with real-time access to the web, data, and more.
MIT ★ 25 -
MCP server for Chilean law — starting with BCN/LeyChile + Contraloría, built to grow, served as LLM-ready Markdown with structured data.
MIT ★ 2 -
Self-hosted web data extraction in Rust: LLM-ready content extraction, SPA recovery via sandboxed JS, robots-aware crawler, extraction quality gates, browser TLS fingerprinting and Cloudflare handling. REST API + MCP server.
AGPL-3.0 ★ 1 -
turbowebfetchgithub.com/aza-ali/turbowebfetchupdated this year
Turn websites into LLM-ready data, locally. Handles dynamic JS, Cloudflare, and rendering automatically. 14 parallel browsers. Zero API keys.
npm MIT -
CarbonLensgithub.com/DharmpratapSingh/CarbonLensupdated this year
Production-ready emissions analytics platform combining EDGAR v2024 datasets, Model Context Protocol (MCP) integration, and LLM-powered natural language queries. Analyze multi-sector greenhouse gas data with geographic granularity from cities to countries, 2000-2024.
MIT -
energy-transition-intelligence-mcpgithub.com/apifyforge/energy-transition-intelligence-mcpupdated this year
Energy transition intelligence for AI agents — this MCP server gives any LLM client access to 7 live data sources and 4 scoring models covering energy transition readiness, grid stress prediction, stranded asset risk, and EV infrastructure gap analysis.
MIT -
omega-tools-mcpgithub.com/ranapratapmajee/omega-tools-mcpupdated this year
A production-grade Model Context Protocol (MCP) server engineered for LLM agents. Features highly modular, XML-isolated toolkit pipelines that eliminate formatting bias across custom data lookups and external API actions. Ready for standard local Stdio IDE workflows or scalable, multi-container SSE Docker network meshes.
-
Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-fingerprint stealth to bypass anti-bot filters, CSS/XPath parsing, and 24 built-in scrapers, clean, structured, LLM-ready data from any URL.
pypi MIT ★ 265 -
Serverless annotation framework with LLM pre-labeling, inter-annotator agreement analysis & offline HTML interface. CLI + MCP ready.
MIT -
Automated dataset reverse engineering framework — 6-stage analysis pipeline, LLM-enhanced cost modeling & 23+ production documents. CLI + MCP ready.
MIT -
cockroach-crawlergithub.com/ajnasnb/cockroach-crawlerupdated this year
Give AI agents superpowers on the web: crawl, render, map, extract, and verify evidence through one governed Node.js crawler.
npm MIT -
Tidbitgithub.com/phanii9/Tidbitupdated this year
Capture anything into structured Markdown notes and training-ready JSONL.
pypi MIT ★ 8 -
A database's schema grounded in its data and described in sentences, ready for a text to SQL agent to read
Apache-2.0 ★ 1 -
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
MIT ★ 2 -
Three agent-economy products: a GovCon data feed with MCP + x402, an agent-readiness audit engine, and an archive-to-plan tool
-
Multi-source async competitive intelligence engine for AI training data ecosystems with watermark-driven incremental scanning & anomaly detection. CLI + MCP ready.
MIT ★ 3 -
ai-playbookgithub.com/muriloscigliano/ai-playbookupdated this year
78 engineering patterns + 17 design principles + structured data layer for building AI-first products. MCP server, CLI, web UI.
MIT -
vertica-mcpgithub.com/zaboura/vertica-mcpupdated this year
Production-ready MCP server for Vertica—secure tools, row streaming, pagination, and system metrics for LLM agents (Claude, Cursor, VS Code).
pypi Apache-2.0 -
Gymnasium-style RL framework for LLM agent training — MDP environments, three-layer process reward & SFT/DPO/GRPO policy optimization. CLI + MCP ready.
★ 4 -
veroq-mcpgithub.com/Veroq-ai/veroq-mcpupdated this year
Production-ready MCP server for VEROQ — 52 tools for financial intelligence. Ask, verify, search, price, screen, and more.
MIT ★ 3 -
🦎 面向 AI Agent 的生产级爬虫工具:6 级反爬自动升级 / MCP + REST + CLI 三接口 / 自适应降级 / LLM 友好 Markdown | Production-grade web scraping for AI agents: anti-bot escalation, MCP+REST+CLI, LLM-ready Markdown
MIT -
PR readiness gate that scores pull requests against six criteria using live GitHub and PagerDuty data via MCP
-
Model Context Protocol (MCP) Server for Generative Engine Optimization (GEO) & RAG Readiness Audits — by Taqi Molavi
MIT ★ 3 -
15 production data, monitoring and audit APIs on Apify — MCP-ready, pay-per-event, x402/USDC, 30 public task examples with verified outputs
★ 2 -
Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.
Apache-2.0 ★ 56 -
SMKRV-MCP-Studiogithub.com/SMKRV-MCP-Studio/SMKRV-MCP-Studioupdated this year
Turn your database into an AI-ready data source via MCP (Model Context Protocol). Visual SQL tool builder, multi-DB support, Docker all-in-one image.
NOASSERTION -
Local-first MCP server and CLI in Rust: any page as LLM-ready Markdown, whole-site crawls, keyless search, and local captcha solving. No cloud, no API keys.
npm AGPL-3.0 ★ 21 -
OpsPulse-MCP-Operational-Intelligence-Dashboardgithub.com/jaidevreddy/OpsPulse-MCP-Operational-Intelligence-Dashboardupdated this year
OpsPulse MCP is a config-driven operational intelligence dashboard with an MCP-style backend and a modern frontend UI. It helps track incidents/tickets, compute health scoring, and generate executive-ready summaries using an LLM.
-
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
pypi MIT ★ 8 -
Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格,并支持 StatsPAI 跨栈交叉验证。
pypi MIT ★ 55