Base L2 Agent Kit

BackEngine is a multi-tenant SaaS platform that ingests all of an organization's customer and prospect communications — Slack threads, emails, call and meeting transcripts, and support tickets — and distills them into structured, queryable context. Raw conversations are processed into signals (categorized, attributed moments), sources (the underlying transcripts, emails, and tickets), and rolling project overviews, all isolated per tenant and scoped by role and access controls. The MCP server exposes this layer over the Model Context Protocol, so an LLM client can query customer signals, reconstruct context, prep for meetings, surface at-risk accounts, and draft grounded outreach from real conversation history — without leaving the chat

Monitor AI output schemas and API contracts for breaking changes — validate LLM JSON responses against defined schemas on a schedule

An MCP server that provides a tool for sending transactional emails via Mailtrap

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Market & supply-chain intelligence for 30+ humanoid robots: viability scores, specs, pricing, deployment status. Free PUBLIC tier; one key for both REST API and MCP.

One API for Search, Crawling, and Sitemaps

MCP-native open-source Notion alternative. Read and write pages, customizable databases, and kanban/calendar boards through a remote MCP server with OAuth 2.1 and a full audit log.

PatSnap Advanced Patent Search MCP is a Model Context Protocol server that connects AI agents to PatSnap's Advanced Patent Search capabilities. Provides flexible and in-depth advanced patent search capabilities. It supports semantic, similarity, image, patent-number, nested-query, analytics, and keyword-assist workflows, enabling experienced users to build and refine complex search strategies efficiently. It is suitable for search specialists, analysts, and demanding research projects.

MCP server for interacting with Neon Management API and databases

PatSnap Patent Legal Status & Annuity MCP is a Model Context Protocol server that connects AI agents to PatSnap's Patent Legal Status & Annuity capabilities. Focused on reviewing patent legal status, annuity status, and core legal documents. It supports annuity payment information, legal status, full text, specifications, claims, and citation-related signals to help determine whether a patent remains in force and whether there are title changes or lapse risks. It is suitable for maintenance management, transaction checks, licensing review, and due diligence.

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI, zero dependencies.

Read-only database access with schema inspection

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。

Find warm LinkedIn leads via AI. Enrich contacts, unlock comments, deliver to Slack.

test

PatSnap Patent Briefing MCP is a Model Context Protocol server that connects AI agents to PatSnap's Patent Briefing capabilities. A quick-read tool for understanding a patent or patent family. It brings together bibliographic data, legal status, family information, the three core technical elements, drawings, and translations of specifications, abstracts, and claims so that even users without a patent background can grasp the key points quickly. It is useful for internal communication, early screening, patent training, and client briefings.

AI image generation using various models

Enigmata MCP provides AI clients with secure access to personalized Enigmata astrological forecasts, including day, week, month, and thematic forecast contexts. Forecasts contain the percentage of favorability of any day and the probability of any event. It helps assistants retrieve structured guidance, compare forecast periods, search themes, check profile readiness, and complete required solar-location setup when needed. Tools get_mcp_capabilities - Returns metadata about the available Enigmata MCP tools and their capabilities. get_day_forecast - Returns an AI-friendly personalized day forecast. get_day_forecast_section - Returns a specific section of a day forecast, useful when a client needs smaller responses. get_week_forecast - Returns an AI-friendly personalized week forecast. get_month_forecast - Returns an AI-friendly personalized month forecast. get_theme_forecast - Returns a forecast for a selected theme, including favorability or probability context. get_theme_best_days - Returns the best days for a selected forecast theme. compare_theme_days - Compares two dates for a selected theme without returning the full theme calendar. get_theme_probability_trends - Returns the subscription-period probability trend for a selected theme. get_theme_catalog - Returns the user’s saved themes and popular available themes. search_themes - Searches forecast themes and returns ranked candidates for precise theme selection. compare_forecasts - Compares two day, week, month, or theme forecast contexts. get_profile_readiness - Returns the user’s profile and onboarding readiness for forecast access. get_solar_requirement - Checks whether a solar meeting city is required for the user’s forecast flow. search_cities - Searches cities that can be used as a solar meeting place. submit_solar_place - Submits the user’s solar meeting city when it is required to unlock or update forecasts.

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

Remote MCP server (Streamable HTTP) giving AI a real cloud file system + web scraping. One static Bearer token; 21 tools incl. chunked/resumable upload, download, list/search, full folder tree (create/move/rename/delete), shareable links, quota, and scrape_url (web page -> clean Markdown). Credit-based, free credits on signup.

Mobile-first, voice-first AI life planner with native MCP. Connect from your AI assistant to read your agenda, create and reschedule tasks, break goals into dated steps across sections, and remember your priorities across sessions. Everything syncs to your real Salta on phone and web. Works with Claude, ChatGPT, Cursor, and Codex. Free — your own assistant does the thinking.

Retrieving and analyzing issues from Sentry.io

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

An agent-first office suite your AI reads and writes over MCP — Docs, Sheets, Slides, a Database, Drive, and Notion-style Pages. Sign in with Google; free to start.

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

Playwright MCP server