Beatlyze

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

Kage is shared, code-grounded memory for developers and their coding agents. Capture a learning once — a bug cause, a decision, a gotcha — and the whole team plus every agent recalls it next time it's relevant. Memory is grounded in your actual code and stored as git-tracked JSON reviewed in PRs, not a personal vector blob that drifts: citations are validated on write, and stale memory (whose code was deleted or refactored) is withheld from recall and flagged for you. Works with Claude Code, Codex, Cursor, Windsurf, and any MCP client. No vector DB, API key, or service to run. Try it in 30s: npx -y @kage-core/kage-graph-mcp demo

bugAgent turns your AI assistant into a full QA engineer. Create and triage bug reports with AI root-cause analysis, manage test cases and runs, write and execute Playwright automations, run security and performance scans, and track team quality metrics — all from Claude, Cursor, or any MCP client. 109 tools covering the full QA lifecycle. Requires a free bugAgent account at app.bugagent.com.

Comprehensive Singapore government data MCP server — typed tools for SG datasets (data.gov.sg and more) for any AI agent.

test

Mercury is a pay-per-call MCP server that lets AI agents discover and call financial data tools using the x402 HTTP payment protocol. 18 tools covering crypto prices, DeFi liquidity, NFT data, on-chain analytics, and more. tools/list is free — tools/call is billed per call using your Mercury API key. Connect by URL: https://network.mercury-hq.com/mcp

Auditable, self-improving knowledge & memory for AI agents, served over MCP. Citation-enforced answers (no source, no claim), a replayable why-trace per answer, and a judge-gated loop that promotes validated knowledge. Zero-key local embeddings (bge-m3), hybrid vector + BM25 retrieval, scoped fail-closed bearer auth, and multi-tenant row-level security — self-hosted on Postgres alone. Apache-2.0. Reference implementation of the Agentic Product Standard.

Your personal listen-later podcast

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

AI image generation using various models

Browser automation and web scraping

GitLab API, enabling project management

European AI orchestration platform — connects CRM, ERP, documents with LLMs. GDPR-compliant, EU-hosted, MCP-native. 4 tools: search_documents, query_database, create_record, send_notification.

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。 如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

An open-source Model Context Protocol (MCP) server for the InvGate Service Desk / Service Management API. Exposes 96 tools across 11 domains — incidents (create, update, comment, reassign, approvals), users & groups, knowledge base, custom fields, assets/CIs, workflows, triggers, breaking news and time tracking. Read-only by default. Write access is opt-in via granular profiles: `support` (incidents + time tracking, KB stays read-only) or `full` (adds Knowledge Base writes). Backward compatible, fail-fast on misconfiguration, with optional OpenTelemetry instrumentation. Install: `uvx invgate-service-desk-mcp`. Published on PyPI and listed in the official MCP registry.

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

Postal mail API for AI agents. mailbox.bot lets agents send outbound physical mail, including letters, certified mail, postcards, and batch mailings, with cost previews, approval controls, tracking, proof artifacts, and signed webhooks. It also supports inbound mail context from forwarded scans, phone-captured postal mail, PDFs, photos, and documents, so agents can understand physical-mail context and generate replies. Get a new receiving mailbox number for your agent with a real street-address opening soon through the mailbox.bot waitlist.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

Automatically create a remote browser to complete your specified tasks, developed based on Browser Use + Sandbox. 自动创建一个远程浏览器，完成你指定的任务，基于Browser Use + Sandbox开发。

Multi-perspective decision reasoning for Claude. When you face a real choice: career, money, relationships, strategy. Orlog examines competing angles and takes a clear position, not a hedge. Get an API key at orlog.fyi.

Provably correct day-count and accrued-interest calculations. A small, dependency-light TypeScript library and an MCP server, so an AI agent can get the exact number instead of guessing.