MCP Servers

Open-source MCP-native browser agent with human takeover via noVNC, reusable auth profiles, and approval/audit rails. Playwright + FastAPI, Docker-based isolated sessions, stdio bridge for Claude Desktop and Cursor.

MCP server bridging Claude Desktop with Selenix for browser automation and testing. Create, run, debug, and manage browser tests through natural language.

MCP server that compiles AI browser automation into deterministic .tap.json plans (25-op closed union, zero runtime LLM), runs on your logged-in Chrome, and detects drift via semantic fingerprint diff when sites change. 65+ open community taps on 40+ sites.

MCP server for screenshots, PDFs, OG images, and narrated video recording from Claude Desktop, Cursor, and Windsurf.

Multi-tier fallback chain for fetching web content as clean markdown. Handles tweets, YouTube, arXiv, PDFs, and regular pages with 9 fallback strategies.

Token-budgeted web fetch for AI agents. Auto-routes between Trafilatura, Jina Reader, FireCrawl, and pypdf based on URL pattern. estimatetokens before fetchurl, 6h Redis cache, server-side maxtokens truncation. Open source MCP server (MIT) plus hosted REST API at agentfetch.dev

Native Safari browser automation for AI agents with 80+ tools. No Chrome dependency, optimized for Apple Silicon with 60% less CPU overhead.

Sleep disruption cause classifier using The Longevity Vault's 5-cause framework. Identifies the biological mechanism behind 3am wakeups from symptom descriptions, with tracked links to the full interactive 3AM Decoder.

Clinical research MCP server for trial coordinators and life sciences teams. Real-time access to PubMed (35M+ papers) and ClinicalTrials.gov (400K+ trials). No API key required.

Taiwan's first public MCP server for National Health Insurance (NHI) data — 234 rejection codes, 1,497 ICD-10→procedure mappings across 20 specialties, audit indicators (008/014/027/P043), and semantic wiki search over 8,232 chunks of official NHI documentation. Powered by OPDSTAR. Install: npx @opdstar/nhi-mc

HEOR (Health Economics and Outcomes Research) MCP server with 7 tools for literature search across 41 medical data sources (PubMed, NICE, CADTH, ICER, etc.), cost-effectiveness modeling (Markov/PartSA/PSA), and HTA dossier preparation for pharmaceutical and biotech teams.

The only MCP server bridging DICOM, HL7v2, and FHIR in one package. Cross-standard mapping, Mirth Connect channel generation, vendor private tag decoding (GE, Siemens, Philips), and integration pattern knowledge. Built by a 19-year healthcare IT veteran. pip install dicom-hl7-mcp

Healthcare billing AI for agents: ICD-10/CPT/HCPCS code lookup (81,769 codes with RVU + OPPS pricing), prior auth prediction, medical NER, claims validation, denial-risk scoring, HIPAA compliance auditing, and NPI/drug enrichment. 20 tools, 10 free credits then pay-per-call via credits or anonym

Multi-agent MCP server for genomic analysis — specialized AI agents analyze raw DNA files across 16 databases (ClinVar, GWAS, gnomAD, CPIC, AlphaMissense, and more) and coordinate findings through shared MCP tools. Privacy-first, runs locally.

AI-native architecture platform for engineering teams. Describe a system in natural language (e.g. "payment service with Stripe, Kafka, PostgreSQL") → get an interactive typed diagram with 167 cloud components → export to 14 production frameworks (Java Spring Boot, Python FastAPI, Go chi, Rust Axum, .NET, Kotlin Ktor, Ruby Ra

Create workflow, sequence, and architecture diagrams using FlowZap Code DSL. 7 tools for validation, playground URL generation, syntax docs, graph export, artifact parsing, diffing, and patching. No API key required. Install via NPM: npx -y flowzap-mcp

MCP server for AI Diagram Maker — generate flowcharts, sequence diagrams, ERDs, system/network architecture, UML, mindmap, and workflow from natural language, code, ASCII, images, or Mermaid. Inline rendering using MCP Apps UI and editable diagram URLs. Requires API key.

Bazi (Four Pillars / 四柱推命 / 사주팔자) charting MCP server with true solar time correction and multilingual output (中文/EN/日本語/한국어). npx shunshi-bazi-mcp

Generate images, video, and audio via 20+ AI models (Flux, GPT-Image-1, Imagen 4, Grok, Seedance, ElevenLabs). Prompt builder with styles, lighting, camera, mood presets. Batch generation support.

Turn natural language into 3D models in Fusion 360. 64 CAD tools including sketches, extrudes, fillets, and JIS standard parts.

Search, read, and discover thousands of visual aesthetics (cottagecore, dark academia, y2k, goblincore, and many more) from the Aesthetics Wiki. Great for moodboards, brand direction, and creative inspiration. uvx aesthetics-wiki-mcp

93-tool Spotify server with smart shuffle, natural language song search, vibe analysis, artist network mapping, taste evolution, and playlist power tools. Works after Spotify's Feb 2026 API changes.

Federated, license-verified search across The Met, Cleveland, AIC, Wikimedia Commons, and Europeana. Strict-default-deny rights gate accepts only CC0 / Public Domain Mark. Tools: search, get, cite (full / caption / short), dynasty/region discovery. npx -y open-museum-mcp

AI-powered image editing through Photopea with 34 tools for documents, layers, text, shapes, filters, effects, and export. npx photopea-mcp-server