MPM-Coding MCP server
Tool-first MCP: AST nav, impact/flow, task chains, memo/recall.
17 stars
Reviews
Write oneNobody has reviewed MPM-Coding yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
MPM-Coding tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 41 days ago12/15
- Maintainer identityregistry namespace matches repository owner6/10
How MPM-Coding compares
Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 40% of 1,301 Productivity servers
- GitHub stars
- 17
- more than 81% of 855 Productivity servers
Install MPM-Coding in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the MPM-Coding repository's README, as published. We do not edit it. Read it on GitHub
MPM-Coding
让 AI 编程从"能演示"变成"能交付"
中文 | English
问题
AI 写代码的快乐,很容易被真实项目剥夺:
"那个函数在哪来着?" → 猜文件路径
"我觉得这样改应该没问题" → 不做影响分析
12 步的任务跑到第 7 步挂了 → 没有检查点,无法续传
"上周为什么改这个?" → 谁都说不清MPM 不负责让模型变聪明。MPM 负责把活干完。
📄 想看工程深度? 阅读 技术白皮书 —— AST 引擎、5 层搜索降级、BFS + Dice Random Walk 影响分析、贝叶斯置信度演化……13 章拆解每一个核心设计。
安装
从 Release 安装
从 Releases 下载:
解压。让 MCP 客户端指向 mpm-go。完事。
从 MCP Registry 安装
已在 MCP Registry 发布:io.github.halflifezyf2680/mpm-coding
从源码编译
git clone https://github.com/halflifezyf2680/MPM-Coding.git
cd MPM-Coding
powershell -ExecutionPolicy Bypass -File scripts\build-windows.ps1 # 或 ./scripts/build-unix.sh快速开始
让 MCP 客户端指向 mcp-server-go/bin/mpm-go(.exe),然后:
1) initialize_project
2) 没有了——MPM 协议会自动注入项目根 AGENTS.md 顶部,客户端自动加载
3) 直接提需求——AI 会自动按协议执行就这样。工具编排交给 AI,决策权在你手上。
使用示例
把这段直接贴进 MCP 客户端:
任务:修复 UserService.getProfile 的空指针崩溃。
要求:
1. 用 code_search 定位函数
2. 用 code_impact 检查谁在调用它
3. 修复 Bug
4. 用 memo 记录为什么这样改AI 会自动执行:initializeproject → codesearch → code_impact → 改代码 → memo。
原理
定位 分析 执行 记录
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ │ │ │ │ │ │ │
│ code_ │──▶│ code_ │──▶│ task_ │──▶│ memo │
│ search │ │ impact │ │ chain │ │ │
│ │ │ │ │ │ │ │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
AST 精确 调用链 分阶段 SSOT
符号定位 风险评估 门控验收 变更日志每次修改必须走:找定位 → 查影响 → 改代码 → 记原因。 不猜。不盲改。不留死角。
为什么用 AST 索引而不是 LSP
AI 编程的核心瓶颈不是模型能力,是上下文窗口里的垃圾太多。
一个 5000 文件的项目,AI 如果靠读文件来理解代码,它要么全读(token 爆炸),要么猜着读(遗漏关键依赖)。两种都是灾难。LSP 解决的是 IDE 的人机交互问题——补全、跳转、重命名。这些东西 AI 客户端自己就能做。
MPM 解决的是另一个问题:如何用最少的 token 让 AI 精确理解代码结构。
codesearch 返回的是符号定义的精确位置,不是一堆 grep 结果。codeimpact 返回的是调用链全景,不是让 AI 一个文件一个文件地猜谁调了它。flowtrace 返回的是业务逻辑主链路,不是目录列表。这些工具的 output** 本身就构成了对上下文的清洗——只注入确定性的结构信息,把噪声过滤掉。
这就是注意力收敛:AI 不再需要在大片代码中盲目搜索,工具的输出已经把它的注意力聚焦到必须关注的那几个符号和关系上。真正有价值的不是底层用了什么解析器,而是这些结果被注入上下文后产生的作用。
工具箱
导航
安全
执行
记忆
系统
文档
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
MPM-Coding: common questions
- Is MPM-Coding MCP server safe?
- Mostly: it is graded B (75/100). Read the MPM-Coding safety report
- Does MPM-Coding need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is MPM-Coding maintained?
- The last commit was 61 days ago (2026-09-05). The latest release is v2.11.0.
- What can I use instead of MPM-Coding?
- Servers from other publishers that do the same job: Orbit MCP server, chat-recall MCP server and Argent MCP server.
- How does MPM-Coding compare with other Productivity MCP servers?
- safety score 75/100 (higher than 40% of 1,301 Productivity servers); github stars 17 (more than 81% of 855 Productivity servers). Full comparison.
Alternatives to MPM-Coding
Same job from other publishers: the closest match first, then the best rated.
- OrbitOrbit's local-first task and workflow registry for coding agents.not reviewedGrowingB
- chat-recallOne searchable history across every AI coding tool, with secret scanning and a shared task board.not reviewedGrowingB
- ArgentDrive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agentnot reviewedWidely usedA
- gflow-cliDrive Google Flow from an agent: Veo video and Imagen image generationnot reviewedEstablishedA
- CLEO MCP ServerTask management for AI coding agents — CQRS 2-gateway pattern, 200 ops across 10 domainsnot reviewedEstablishedB