MAA-MCP-Server
Enables control of mobile games via MaaFramework, supporting screenshot, click, swipe, and task execution through MCP protocol.
README
通用手游 Agent
架构和设计详见《通用手游Agent开发文档.md》。第一个落地游戏是无期迷途，资源来自 MBCCtools。
环境准备
python -m venv .venv
./.venv/Scripts/pip install -r requirements.txt # Windows
# source .venv/bin/activate && pip install -r requirements.txt # macOS/Linux
复制.env.example为.env并填写LLM相关的key（LLM_MODEL_ID/LLM_API_KEY/LLM_BASE_URL）。
模拟器/真机需开启adb调试，且games/无期迷途/profile.yaml里的adb.address要能连上；
如果本机装了多个adb，建议在profile里显式填adb.adb_path，否则会用
maa.toolkit.Toolkit.find_adb_devices()自动探测。
单独测试MAA-MCP-Server
不经过LLM，先验证MaaFramework这一层能不能跑通：
./.venv/Scripts/python core/maa_mcp_server.py games/无期迷途/profile.yaml
进程会常驻并通过stdio等待MCP客户端连接（比如用MCP Inspector连上去手动调用
screenshot/click/swipe/list_known_tasks/run_known_task）。
跑自由探索Agent
./.venv/Scripts/python core/agent_runner.py games/无期迷途/profile.yaml
agent_runner.py会自动拉起maa_mcp_server.py子进程（通过stdio），把它暴露的工具注册进
HelloAgents的ReActAgent，然后开始自由探索。探索记忆存在exploration_logs/<game_id>.json里，
按game_id分文件，重复运行不会互相污染。
运行时终端会打印一个本地网页地址（默认http://127.0.0.1:8765），浏览器打开就能实时看到
LLM调用/工具调用/敏感界面拦截等日志（core/log_broadcaster.py，给ReActAgent自带的
TraceLogger包了一层SSE推送，不影响原有的memory/traces/落盘）。端口可以在profile.yaml里加
dashboard: {host: ..., port: ...}覆盖。
接入新游戏
复制games/_template/，按里面的README checklist填。验证标准：接入过程中core/目录
不应该有任何改动。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.