FM Memory MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FM Memory MCP ServerFind the player with 17 crossing, 20 dribbling and 19 shooting, then set crossing to 20"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FM Memory MCP Server
通过 Model Context Protocol 让 AI 读写游戏内存里的球员数据。
10 个工具,覆盖属性读写、对象定位、内存搜索。
安装
pip install numpyPython 3.9+,Windows x64。
Related MCP server: memscope-mcp
配置
{
"mcpServers": {
"fm-memory": {
"command": "python",
"args": ["<本目录>/fm26_mcp_server.py"]
}
}
}工具
工具 | 参数 | 作用 |
| — | 进程 PID、模块基址、内存访问权限 |
| — | 属性索引表(编号 ↔ 中英文名) |
|
| 按若干属性值反查球员对象地址 |
|
| 读某球员全部属性 |
|
| 改单项 |
|
| 批量改 |
|
| 扫全内存枚举球员对象 |
|
| 解析 ID/名字记录表 |
|
| 读原始字节 |
|
| 搜 32 位整数值 |
用法
读一个球员的属性
fm26_find_player(attributes={"传中":17, "盘带":20, "射门":19})
# → {"found": 2, "players": [{"obj": "0x1575a7c0898", ...}]}
fm26_get_attributes(obj="0x1575a7c0898")
# → {"display": {"传中": 17, "盘带": 20, "射门": 19, ...}}改属性
fm26_set_attribute(
signature={"传中":17, "盘带":20, "射门":19},
attribute="传中",
value=20
)
# → {"success": true, "written": 5, "copies": 5}signature 用来定位球员(3~6 项属性足够唯一锁定),写入会自动覆盖该球员在内存中的全部副本。
批量改
fm26_set_attributes(
signature={"传中":17, "盘带":20, "射门":19},
changes={"传球":20, "远射":20, "任意球":20}
)枚举所有球员对象
fm26_list_players(min_mean=60, limit=20)
# → 按属性均值筛选,返回 20 个对象地址按字节读内存
fm26_read_memory(address="0x1575a7c0898", size=64)
# → {"hex": "28 98 20 1d fa 7f 00 00 ..."}搜值
fm26_search_memory(value=100)
# → {"hits": 50, "addresses": ["0x...", ...]}结构
fm26_mcp_server.py MCP 协议层 + 10 个工具 + 内存扫描
fm26_attributes.py 属性表 + 显示值换算 + 读写
fm26_offsets.py 偏移常量
fm26_locate.py 按属性值定位对象
fm26_write.py 写入,自动覆盖全部副本
fm26_table.py ID/名字记录表解析依赖:
fm26_mcp_server → fm26_attributes / fm26_locate / fm26_write / fm26_table
↓
fm26_offsetsLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
- LogRackOAuthai.lograck
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Cross-tool persistent memory and context for AI assistants over MCP.
Shared long-term memory vault for AI agents with 20 MCP tools.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables LLM-driven text game state management by exposing MCP tools for managing players, locations, items, entities, and abstract concepts.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to perform low-level Windows process memory research, including process attachment, memory scanning, reading/writing, pointer chasing, remote code execution, and inline hooking via MCP tools and Lua scripting.4MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that exposes dynamic binary instrumentation, memory editing, pointer scanning, and scripting capabilities to AI agents, enabling real-time process inspection and modification.MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI to directly control Cheat Engine for process attachment, memory scanning, reading/writing, address list management, speed hack, Lua/Auto Assembler execution, and CT file management via the MCP protocol.5MIT