mcp-server-demo

AI agents propose database schema and data changes as reviewable requests before anything is applied — no direct write access. Works with Claude Code, Cursor, and any MCP client.

A full-featured secure MCP server for local file system operations, with built-in image processing, OCR and media tools. 1. Basic uvx startup commands Short command (recommended) # Default stdio mode, unrestricted full filesystem access uvx fsext-mcp-server # Lock all operations to a dedicated workspace (production security recommended) uvx fsext-mcp-server --lock-root /your/workspace Full complete command # Stdio mode with workspace isolation uvx fsext-mcp-server --transport stdio --lock-root /your/workspace # Remote SSE streaming service uvx fsext-mcp-server --transport sse --host 0.0.0.0 --port 8000 --lock-root /your/workspace # Modern Streamable HTTP remote service uvx fsext-mcp-server --transport http --host 0.0.0.0 --port 8000 --lock-root /your/workspace 2. Traditional installation & launch via pip Install published PyPI package pip install fsext-mcp-server Launch commands after pip installation # Default stdio local mode fsext-mcp-server-py fsext-mcp-server # Short alias fsext-py fsext # Secure workspace locked mode fsext --lock-root /your/workspace # Remote SSE streaming server fsext --transport sse --port 8000

A Linux system monitoring server built on the [Model Context Protocol (MCP)](https://modelcontextprotocol.io). Provides real-time system information - CPU, memory, disk, network, processes, Docker, and more - via MCP tools over STDIO transport.

Multi-site analytics for AI agents. Read-only GA4, Search Console, Cloudflare edge, and PageSpeed data across every site you run, plus audits that return paste-ready fixes. Local stdio server via npx -y fleets-mcp; pairs with the fleets CLI (npm: fleets).

This application exposes a public, read-only MCP interface to Finnish public procurement law and case law. Available data: 1) Keywords — the Market Court procurement keyword vocabulary in Finnish and Swedish, totalling 412 keywords. 2) Public Procurement Act provisions — the Act on Public Procurement, linked per keyword. 2) Government proposal — HE 108/2016, reasoning per keyword. 3) Case-law summaries — one synthesised summary per keyword of relevant Market Court decisions. Summaries are currently available for 22 keywords (the most common grounds for procurement appeals). Each summary references up to 15 selected Market Court decisions. 4) MAO decision summaries — individual Market Court procurement rulings with metadata and Finlex links.

self-hosted product + web analytics in one go binary. ask it questions from claude code / cursor over mcp, get exact computed numbers (not hallucinated sql). mit, your data stays on your box.

Generate and decode QR codes & barcodes over MCP. qr_generate encodes text/URL into a QR PNG; barcode_generate renders 1-D barcodes (code128/ean13/upc-a/code39/isbn13); qr_decode reads the QR text from an image. Pure server-side, credit-based.

RadMail is an email operating system for agents. Over MCP it searches your real inbox (sender/subject/content, ranked), surfaces a "Right Now" lane, tracks commitments, and drafts reviewable replies. No tool can auto-send money, change banking, or make first contact — human-only forever (BEC defense), published as a machine-verifiable contract at radmail.ai/.well-known/agent-safety.json. Zero-auth sandbox to try in one call: https://radmail.ai/api/mcp/sandbox. Docs: https://radmail.ai/for-agents

Arkitect-MCP brings architecture-first reasoning to your AI coding workflow. Instead of jumping straight to refactors, the server scans repo context first — platform, workload, health, and intent — then returns actionable cursorGuidance for the agent to follow. Tools: repo diagnosis, architecture/pattern/remix catalogs, requirement tags, refactoring analysis, codebase verification, and test runs. Resources: arkitect:// URIs for diagnosis, policy, and catalog data. Local stdio transport via Node.js. Optional Windows desktop app for guided Cursor install. Open source on GitHub — clone, build, and connect in minutes.

GitHits MCP is an OSS context layer for the full software development lifecycle, giving AI agents access to code search, package docs, real-world examples, dependency metadata, vulnerabilities, changelogs, and upgrade evidence.

Connect your portfolio to Claude, ChatGPT, or Codex to analyze it and make smarter investments.

A high-performance, secure, and production-grade Model Context Protocol (MCP) server built with TypeScript, providing comprehensive filesystem operations, advanced text search & replace, image processing, and Tesseract OCR capabilities. Designed for LLM agent integration, it delivers strict input validation, standardized response structures, streaming large-file processing, and multi-transport remote deployment support. Core Features Full Filesystem CRUD & Directory Management：Complete file/directory creation, deletion, copy, move, metadata query, and existence verification. Supports recursive full-directory tree replication and safe move operations with conflict protection. Streaming File I/O for Large Files：Implements segmented text reading, chunked binary streaming reading, text/binary overwriting and appending. Avoids full memory loading, perfectly supporting GB-level large file processing. Advanced Text Search & In-Place Replace：Directory-wide recursive content search, single/multi-file contextual matching with preview lines, regular expression support, case-insensitive matching, and precise in-file text replacement with change statistics. Professional Image Processing Suite：Built-in high-performance image resize (aspect ratio lock support), precise crop, and arbitrary-angle rotation based on Sharp, covering mainstream image editing scenarios. Cross-Platform Tesseract OCR：WASM-first OCR recognition with customizable local Tesseract binary and tessdata paths, supporting multi-language text extraction from images without local engine installation dependency. Strict Strict Input Validation & Standardized Response：All tool schemas enable strict additional property prohibition, with unified success/error response structures for consistent client parsing and error handling. Multi-Standard MCP Transports：Natively supports three official MCP transports: stdio (local client), SSE (legacy remote stream), Streamable HTTP (modern bidirectional remote transport). Full TypeScript Type Safety：Complete type definitions for all tool parameters, response structures, and transport configurations, ensuring runtime stability and development friendliness. 1. Run without installation npx -y fsext-mcp-server --lock-root /your/workspace # Default STDIO transport with lock root support npx -y fsext-mcp-server --transport stdio npx -y fsext-mcp-server --transport http --host 0.0.0.0 --port 8080 --origin * # Streamable HTTP transport npx -y fsext-mcp-server --transport sse 2. Installation Global Installation (Recommended for CLI Usage) npm install -g fsext-mcp-server Local Project Installation npm install fsext-mcp-server 3. Startup Commands 3.1. Default Stdio Mode (For Claude Desktop / Cursor / Local MCP Clients) # Default stdio transport for local agent integration fsext-mcp-server-ts fsext-mcp-server # Short alias fsext-ts fsext 3.2. SSE Remote Transport Mode fsext-mcp-server --transport sse --host 0.0.0.0 --port 8000 Endpoints: SSE Stream Subscription:http://<host>:<port>/sse Client Request Channel: http://<host>:<port>/messages 3.3. Modern Streamable HTTP Transport Mode fsext-mcp-server --transport http --host 0.0.0.0 --port 8000

Text, push, or call your phone when an agent needs input mid-task. Reply by voice instead of babysitting a long-running or blocked terminal.

Image toolkit over MCP: img_info, img_resize, img_compress, img_crop, img_watermark. Resize, compress/convert, crop and watermark images (CJK text OK); outputs saved with download URLs.

Query, profile, and convert CSV/JSON/Parquet data files with SQL over MCP — server-side DuckDB returns answer rows an AI cannot compute in-context.

memo is a local-first, long-term semantic memory for AI coding agents (Claude Code, Cursor, Cline, Codex). Runs fully offline with in-process embeddings — MLX on Apple Silicon or CPU sentence-transformers on Linux/Docker — and a sqlite-vec + BM25 hybrid retrieval pipeline with reranking. Markdown files on disk are the source of truth; the SQLite index is a rebuildable derivative. Includes a recall hook that auto-injects relevant memories every prompt, an MCP server (memo-mcp), a CLI (memo), a knowledge graph, temporal/time-machine queries, contradiction detection and nightly synthesis. No cloud, no API keys. Install: pipx install mlx-memo

Search Shopify store intelligence, enrich domains, preview decision-maker contacts, and reveal approved contact channels from AI clients.

AgentBodega MCP gives agents a free discovery and handoff layer for AgentBodega's paid x402 HTTP resources. Agents can search available services, compare endpoint prices, inspect accepted and required inputs, review output examples, and generate curl/JavaScript call snippets. Paid execution stays on AgentBodega's hosted HTTP endpoints so blockchain settlement, receipts, and live catalog metadata remain auditable.

The social network where AI agents and humans are both first-class members — agents post, follow, hire, and create via API/MCP. 23 tools: zero-credential agent signup, posting, feeds, DMs, scheduling, webhooks, and the Digital Entity directory. Docs: https://circuitai.social/docs

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

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

TmpState (temp state) - a tokenless temporary JSON database. One curl creates a database; the URL is the only credential. No signup, no API keys, 24h free, $1 to keep for a week. Also a zero-key MCP server: https:// tmpstate.dev/mcp

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

All-in-one Amazon scraping MCP for real-time ad tracking, keyword monitoring, and VOC review intelligence.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.