ai-readme-mcp 0.4.2 → 0.4.4

package/README.md

@@ -10,7 +10,7 @@
 
 **AI_README MCP Server** is a Model Context Protocol (MCP) server that helps AI assistants understand your project conventions through dedicated `AI_README.md` guide files. It automatically discovers, routes, and manages these files so AI can generate consistent, high-quality code that matches your team's standards.
 
-**Works with:** Cursor, Claude Code, and other MCP-compatible AI tools.
+**Works with:** GitHub Copilot (VSCode 1.102+), Claude Code, Cursor, and other MCP-compatible AI tools.
 
 ---
 
@@ -20,9 +20,9 @@ When working with AI assistants (like Claude, GPT, or other AI coding tools), yo
 
 - ❌ **Inconsistent code style** - AI generates code that doesn't match your project's conventions
 - ❌ **Repeated instructions** - You have to tell the AI the same rules over and over
-- ❌ **Team inconsistency** - Different team members get different AI outputs
+- ❌ **Team inconsistency** - Different team members get different AI outputs, leading to fragmented code quality
 - ❌ **Context loss** - AI forgets your project's specific patterns and best practices
-- ❌ **Outdated documentation** - Project conventions change, but documentation lags behind
+- ❌ **No single source of truth** - Team conventions exist in Slack messages, PRs, and people's heads, not in a format AI can use
 
 ## 💡 The Solution
 
@@ -32,13 +32,15 @@ Think of it as:
 - 📖 A "style guide" that AI reads before writing code
 - 🎓 An "onboarding document" that teaches AI your project's conventions
 - 🔧 A "configuration file" for AI behavior in your codebase
+- 🤝 A **"team contract"** that ensures every developer's AI assistant follows the same standards
 
 ### How It Works
 
 1. **Create** `AI_README.md` files in your project (root or specific directories)
 2. **Document** your conventions: coding standards, architecture patterns, naming rules, testing requirements
-3. **AI reads it automatically** before making changes - ensuring consistent, high-quality output
-4. **Keep it in sync** - AI can update the README as your project evolves
+3. **Commit to git** - Share conventions with your entire team
+4. **AI reads it automatically** before making changes - ensuring every team member's AI follows the same rules
+5. **Keep it in sync** - AI can update the README as your project evolves
 
 ### What This MCP Server Does
 
@@ -58,6 +60,7 @@ This MCP (Model Context Protocol) server automates the entire workflow:
 
 - 🔍 **Automatic Discovery** - Scan and index all AI_README.md files in your project
 - 🎯 **Smart Context Routing** - Find relevant README content based on file paths
+- 🤝 **Team Consistency** - Every team member's AI assistant reads the same conventions from git, ensuring uniform code quality
 - 🚀 **Guided Initialization** - `init_ai_readme` tool scans for empty files and guides AI through population
 - 🔄 **Update & Sync** - AI can both read and update AI_README files
 - ✅ **Validation & Quality** - Ensure README consistency with token limits and structure checks
@@ -75,7 +78,7 @@ This MCP (Model Context Protocol) server automates the entire workflow:
 In your project directory, run:
 
 ```bash
-claude mcp add --scope project ai-readme-manager npx -- ai-readme-mcp
+claude mcp add --scope project ai-readme-manager npx -- -y ai-readme-mcp
 ```
 
 This creates a `.mcp.json` file that uses `npx` to run the package - no installation or path configuration needed!
@@ -140,6 +143,36 @@ Add to Cursor's MCP configuration file:
 
 After configuring, restart Cursor completely.
 
+### For GitHub Copilot (VSCode 1.102+)
+
+**Requirements:**
+- VSCode 1.102 or later
+- GitHub Copilot & Copilot Chat extensions installed
+
+**Option 1: Using VSCode Settings UI**
+
+1. Open VSCode Settings (Ctrl+,)
+2. Search for "MCP"
+3. Click "Edit in settings.json"
+4. Add the MCP server configuration
+
+**Option 2: Manual Configuration**
+
+Add to your VSCode `settings.json`:
+
+```json
+{
+  "github.copilot.chat.mcp.servers": {
+    "ai-readme-manager": {
+      "command": "npx",
+      "args": ["-y", "ai-readme-mcp"]
+    }
+  }
+}
+```
+
+After configuring, restart VSCode and you'll see the MCP tools available in GitHub Copilot Chat!
+
 ### For Claude Desktop Application
 
 Add to `claude_desktop_config.json`:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-readme-mcp",
-  "version": "0.4.2",
+  "version": "0.4.4",
   "description": "MCP server for managing AI_README.md files in projects",
   "type": "module",
   "bin": {
@@ -45,8 +45,12 @@
     "readme",
     "context",
     "claude",
+    "copilot",
+    "github-copilot",
+    "cursor",
     "llm",
-    "model-context-protocol"
+    "model-context-protocol",
+    "vscode"
   ],
   "author": "Draco Cheng <draco.cheng@outlook.com>",
   "license": "MIT",