Neo4j MCP Clients & Servers

Alpha Sophia MCP Server brings trusted healthcare commercial intelligence to AI agents through the Model Context Protocol (MCP). Purpose-built for life sciences, pharmaceutical, biotech, MedTech, diagnostics, and digital health teams, it enables AI assistants like ChatGPT, Claude, Cursor, and any MCP-compatible agent to query live, claims-grounded healthcare data instead of relying on outdated model knowledge. With access to 4+ million U.S. healthcare providers, healthcare organizations, and sites of care, the Alpha Sophia MCP Server powers AI workflows for HCP targeting, physician segmentation, KOL identification, market sizing, territory planning, commercial operations, medical affairs, market access, sales planning, referral intelligence, and clinical trial site identification. Teams can search providers by specialty, procedure volume (CPT/HCPCS), diagnoses (ICD-10), prescribing behavior, affiliations, publications, clinical trials, geography, and dozens of other commercial attributes—all through natural language. Unlike generic AI tools, every response is grounded in governed, all-payer U.S. healthcare claims data, giving life sciences organizations reliable answers for commercial decision-making. Whether you’re building autonomous AI agents, custom healthcare copilots, or AI-powered GTM workflows, Alpha Sophia’s MCP Server provides the trusted healthcare data layer needed for enterprise-grade life sciences AI applications. (alphasophia.com⁠)

The MCP server that vets MCP servers. Connect your agent to the PolicyLayer registry and check any MCP server's identity, risk grade, auth posture and tool classifications before installing it. Free single-server lookups over 32,500+ published servers and 515,000+ classified tools, kept current by continuous scanning.

Remove the "Made with Gamma" watermark from PDF/PPTX exports — structural, lossless. Local stdio server (files never leave your machine) or hosted endpoint at https://gammaremover.com/mcp. Free web version: gammaremover.com

Live European funding data inside your AI. EUACC's MCP connector gives Claude, ChatGPT, Grok and Claude Code 14 tools for EU funding: open grant calls (refreshed daily from the EU Funding & Tenders Portal), full details on every EU programme (Horizon Europe, EIC, Digital Europe, LIFE, Innovation Fund, CEF), per-sector and per-country funding landscapes, how-to guides, 78,000+ Horizon Europe consortium partners from CORDIS, European Digital Innovation Hubs and incubators, 1,200+ European VC funds, and a directory of EU-funded startups. Free to use: create an EUACC account, generate a connector key, add the endpoint https://www.euacc.ai/api/mcp to your AI, and ask anything about EU funding. Your intellectual property never leaves your side — EUACC is a data connector, not a ghostwriter. Learn more and connect at https://www.euacc.ai/ai-tools

Browser automation and web scraping

Buildy is a home for all the apps your agent builds you.

Write notes to Flomo

Runware MCP Server connects Claude, Cursor, Codex, VS Code, and other MCP clients directly to Runware's content generation API. It exposes tools for full-featured image inference, upscaling, background removal, captioning, and masking, plus text-to-video and image-to-video generation. A hosted version is available at mcp.runware.ai with OAuth sign-in, or run it locally via npx @runware/mcp with your own API key.

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

LLMs give wrong answers from documents because the extracted text is broken: split words, lost tables, page furniture, and scanned pages that come out empty. PackForAI turns PDF, DOCX, PPTX, XLSX, CSV and JSON into clean, AI-ready Markdown — rejoining words, rebuilding reading order, recovering scanned pages with OCR, and stripping noise. You get compact Markdown plus a before/after token count (typically up to 65% smaller). Use it from the web app, the REST API, an open-source MCP server (Claude & Cursor), or the CLI. Files are stored in the EU, private to you, and never used to train AI.

Read-only MCP server that lets your coding agent see the sibling repositories next to the one it's working in overview, search, read, zero write tools. Security by architecture: path traversal, symlink escapes and secret files are blocked, proven by tests.

Discover ranked, actively-maintained Claude and MCP tools by task. Query the Claudeers ecosystem registry directly from your agent — search_tools returns tools with health status, community ratings, and merit-only ranking, so you find what actually works instead of a raw keyword search. get_tool and list_categories round out discovery. Read-only, no auth, remote HTTP.

MCP Advisor & Installation - Use the right MCP server for your needs

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

Read-only database access with schema inspection

Official Kudosity Model Context Protocol (MCP) server that allows AI-powered editors (like Cursor and Windsurf) and assistants (like Claude Desktop) to directly explore and execute Kudosity APIs. With MCP, your AI can search API specs, generate code snippets, and run live requests; all without leaving your development environment.

AgentRank is the settlement-grounded trust check for AI agents. Before your agent pays, hires, or extends credit to another agent or x402 service, call check_agent_trust to see if it is real and settlement-backed: a 0-1000 reputation score computed from real on-chain USDC settlement (sybil-resistant, continuously stress-tested against collusion). Also: gate_caller (gate your own service by a caller's rank), classify_x402_address (real service vs rail vs treasury vs dust), and state_of_x402 (the de-noised census of the whole x402 economy). 78% of x402 counterparties are unverifiable ghosts; AgentRank tells you which are real. Free, read-only, no API key. By Crest Deployment Systems.

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.

Data and execution layer for tokenized real-world assets (RWAs) on Injective. Open catalog tools expose indexed assets, live market data, price history, routable venues, and a 6-dimension risk score (backing, enforceability, control, exit, liquidity, social) for every asset. Trading tools (buy, sell, deposit, withdraw) work via lazy OAuth — the first trade call triggers sign-in with Realmint and a one-time wallet delegation; trades are then signed server-side under a spending cap, with no API keys or seed phrases in the client. Also supports x402 pay-per-call funding for agents.

Web content fetching and conversion for efficient LLM usage