CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

MPM-Coding

halflifezyf2680/mpm-coding
15STDIOregistry active
Summary

A code intelligence server built on AST indexing rather than LSP, designed for AI coding workflows where context window efficiency matters. Exposes `code_search` for symbol lookup, `code_impact` for call graph analysis (upstream/downstream), `flow_trace` for execution path mapping, and `task_chain` for checkpointed multi-step workflows. The memo/recall system persists decision history across sessions. Ships with a Tree-sitter based indexer supporting 30+ languages, SQLite persistence, and generates `_MPM_PROJECT_RULES.md` to guide tool orchestration. Reach for this when you're tired of AI agents guessing at file locations or missing blast radius on refactors. The whitepaper details BFS impact analysis and search degradation strategies if you want the internals.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

MPM-Coding

让 AI 编程从"能演示"变成"能交付"

中文 | English

License Go MCP Platform Languages


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:

平台文件
Windows x64mpm-windows-amd64.zip
Linux x64mpm-linux-amd64.tar.gz
macOS Universalmpm-darwin-universal.tar.gz

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) 把生成的 _MPM_PROJECT_RULES.md 放进客户端系统规则
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:

读取 _MPM_PROJECT_RULES.md 并严格遵守。

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:initialize_project → code_search → 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。

code_search 返回的是符号定义的精确位置,不是一堆 grep 结果。code_impact 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。flow_trace 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

工具干什么
code_search精确定位符号。不是 grep,是 AST 级精确查找。
project_map一眼看到目录结构和符号清单。
flow_trace追踪函数调用链——改代码之前先看懂主链路。

安全

工具干什么
code_impact"谁调用了它?" 或 "它调用了谁?"——动手前先看爆炸半径。

执行

工具干什么
task_chain长任务?拆成阶段,每阶段有门控验收。会话断了也能续。
system_hook被阻塞?挂个钩子,条件满足后再继续。

记忆

工具干什么
memo记录"为什么改"。跨会话持久保留。
system_recall"之前是不是修过类似的?"——搜索历史记录。
known_factsKnownFact 策略引擎:行动前召回经验,行动后回写结果并进化。

系统

工具干什么
initialize_project初始化 AST 索引 + 生成项目规则。一次性操作。
index_status查看后台索引进度。
ensure_languages下载缺失的 tree-sitter grammar。通常自动执行。
persona切换 AI 人格,适配不同场景。

文档

文档说明
docs/WHITEPAPER.md技术白皮书——AST 引擎、搜索策略、置信度演化、影响分析算法,看 MPM 的工程深度
docs/MANUAL.md完整手册——全部工具、参数、案例
QUICKSTART.md5 分钟上手指南
docs/WHITEPAPER_EN.mdEnglish whitepaper
docs/MANUAL_EN.mdEnglish manual
README_EN.mdEnglish overview

架构

查看交互式架构图

mcp-server-go/
├── cmd/server/main.go              # 入口 (StdIO MCP Server)
├── internal/
│   ├── tools/    (14 files)        # MCP 工具实现
│   ├── core/     (6 files)         # 数据层 — SQLite + MemoryLayer (SSOT)
│   └── services/                    # AST 索引器 (Tree-sitter, 多语言)
└── configs/                         # 默认配置
  • Go 1.21+ — 零 CGO,纯 modernc.org/sqlite
  • Tree-sitter — Rust AST 索引器,30+ 语言按需下载
  • SQLite — 嵌入式存储,数据在 .mpm-data/(不提交到 git)

常见问题

问题用什么
怎么找函数/类?code_search
改代码前怎么查影响范围?code_impact
怎么看懂一个模块的调用链?flow_trace
长任务怎么可靠执行?task_chain
大仓库索引进度怎么看?index_status
怎么强制全量索引?initialize_project(force_full_index=true)

完整手册:docs/MANUAL.md


许可证

MIT

本项目使用 tree-sitter(MIT License)进行 AST 解析。

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
Productivity & Office
Registryactive
Packagehttps://github.com/halflifezyf2680/MPM-Coding/releases/download/v2.9.0/mpm-coding-v2.9.0.mcpb
TransportSTDIO
UpdatedMay 28, 2026
View on GitHub

Related Productivity & Office MCP Servers

View all →
Office PowerPoint

gongrzhe/office-powerpoint-mcp-server

A MCP (Model Context Protocol) server for PowerPoint manipulation using python-pptx. This server provides tools for creating, editing, and manipulating PowerPoint presentations through the MCP protocol.
1.7k
Office-Word-MCP-Server

gongrzhe/office-word-mcp-server

Exposes Word document operations via MCP to create, edit, format, and analyze documents programmatically.
2k
Microsoft Office

io.github.mindstone/mcp-server-office

Microsoft Office MCP server: read and edit Word documents, Excel workbooks, and PowerPoint files
8
Todoist

greirson/mcp-todoist

MCP server that connects Claude to Todoist for natural language task and project management with bulk operations
240
Mcp Apple Notes

henilcalagiya/mcp-apple-notes

MCP server for Apple Notes integration using AppleScript with full CRUD operations
51
AnkiMCP Server

ankimcp/anki-mcp-server-addon

Anki addon that exposes your flashcard collection to AI assistants via a local MCP server.
50