@memly/mcp-server 0.2.0 → 0.2.2

package/README.md

@@ -1,16 +1,49 @@
 # @memly/mcp-server
 
-> Persistent memory for any IDE that supports MCP.
+> Persistent memory for IDEs that **don't support custom LLM providers**.
 
-## Supported IDEs
+## Proxy vs MCP — which one should I use?
 
-| IDE | Config File |
-|---|---|
-| VS Code + Copilot | `.vscode/mcp.json` |
-| Cursor | Settings → MCP |
-| Claude Desktop | `claude_desktop_config.json` |
-| Windsurf | Settings → MCP |
-| Zed | Settings |
+Memly has two integration modes:
+
+| Mode | How it works | Best for |
+|------|-------------|----------|
+| **Proxy** (transparent) | Point your IDE's base URL to `api.memly.site` — memory injected in 100% of requests, invisible | IDEs that support a custom OpenAI-compatible endpoint |
+| **MCP server** (this package) | Memly runs as an MCP tool — `load_context` is called automatically at session start | IDEs locked to their own AI service |
+
+---
+
+## Which mode for my IDE?
+
+### ✅ Use the Proxy — supports custom endpoint
+
+| IDE / Tool | Where to configure |
+|-----------|-------------------|
+| **Cursor** | Settings → Models → OpenAI Base URL |
+| **Continue.dev** (VS Code / JetBrains extension) | `config.json` → `apiBase` |
+| **Zed** | `settings.json` → `api_url` |
+| **Aider** | `--openai-api-base` CLI flag |
+| **Jan.ai** | Settings → Model → Engine URL |
+| **LM Studio** | Server settings |
+| **Open WebUI** | Admin → Connections |
+| **Msty** | Settings → Custom provider |
+| **Void** | Settings → Custom provider |
+
+### ❌ Use the MCP server — locked provider, no custom endpoint
+
+| IDE / Tool | Reason |
+|-----------|--------|
+| **VS Code + GitHub Copilot** | Microsoft/GitHub auth — base URL not configurable |
+| **JetBrains AI Assistant** | Locked to JetBrains AI Service subscription |
+| **Windsurf (Codeium)** | Cascade uses Codeium's own models — no external endpoint |
+| **Amazon Q / CodeWhisperer** | AWS-only pipeline |
+| **Tabnine** | Proprietary closed service |
+| **Replit AI** | Built into Replit, no external provider |
+| **Gitpod AI** | Locked to their own service |
+| **Sourcegraph Cody** | Locked on free tier |
+| **Claude Desktop** | Chat app, not an IDE — MCP native |
+
+---
 
 ## Quick Start
 
@@ -18,9 +51,25 @@
 
 Go to [memly.site/dashboard/api-keys](https://memly.site/dashboard/api-keys)
 
-### 2. Configure your IDE
+### 2. Configure your IDE's MCP server
+
+**VS Code / GitHub Copilot** — create `.vscode/mcp.json` in your project:
+
+```json
+{
+  "servers": {
+    "memly": {
+      "command": "npx",
+      "args": ["-y", "@memly/mcp-server"],
+      "env": {
+        "MEMLY_API_KEY": "memly_your_key_here"
+      }
+    }
+  }
+}
+```
 
-**VS Code / Copilot** — create `.vscode/mcp.json`:
+**JetBrains** (IntelliJ, WebStorm, PyCharm…) — create `.idea/mcp.json`:
 
 ```json
 {
@@ -36,8 +85,9 @@ Go to [memly.site/dashboard/api-keys](https://memly.site/dashboard/api-keys)
 }
 ```
 
-**Cursor** — Settings → MCP → Add Server:
-- Command: `npx -y @memly/mcp-server`
+**Windsurf** — Settings → Cascade → MCP Servers → Add:
+- Command: `npx`
+- Args: `-y @memly/mcp-server`
 - Env: `MEMLY_API_KEY=memly_your_key_here`
 
 **Claude Desktop** — edit `claude_desktop_config.json`:
@@ -56,38 +106,42 @@ Go to [memly.site/dashboard/api-keys](https://memly.site/dashboard/api-keys)
 }
 ```
 
-### Automatic Context (Zero Friction) ⚡
+### 3. Run auto-setup once per project
 
-To make your AI agent proactively load context at the start of every session, add this to your `.cursorrules`, `.windsurfrules`, or `GEMINI.md`:
+Writes the instruction file for your IDE so `load_context` runs automatically at every session start:
 
-```markdown
-# Memly Integration
-At the start of every session, you MUST:
-1. Call `memly.search_memories({ query: "current active task", limit: 5 })`
-2. Use this context to understand the project state.
-3. When you make major decisions, call `memly.save_memory`.
+```bash
+npx @memly/mcp-server init
 ```
 
-### Tools
+Auto-detects VS Code, Cursor, Windsurf, Claude Desktop. Run once, never think about it again.
+
+---
 
-| Tool | Description |
-|---|---|
-| `search_memories` | Semantic search across your stored memories |
-| `remember` | Store a new memory (fact, decision, pattern) |
-| `forget` | Delete a specific memory by ID |
-| `list_projects` | List all projects with memory stats |
+## Tools
+
+| Tool | When the AI calls it |
+|------|---------------------|
+| `load_context` | **Automatically at session start** — loads memories from previous sessions |
+| `search_memories` | When you ask about something specific not loaded by `load_context` |
+| `remember` | When you make a decision, solve a problem, or say "remember this" |
+| `list_projects` | When you ask to list or switch projects |
+
+---
 
 ## Environment Variables
 
 | Variable | Required | Default | Description |
-|---|---|---|---|
-| `MEMLY_API_KEY` | ✅ | — | Your Memly API key |
-| `MEMLY_API_URL` | — | `https://api.memly.site` | API base URL |
-| `MEMLY_PORT` | — | `3800` | HTTP transport port |
+|----------|----------|---------|-------------|
+| `MEMLY_API_KEY` | ✅ | — | Your Memly API key (`memly_...`) |
+| `MEMLY_API_URL` | — | `https://api.memly.site` | Override for self-hosted deployments |
+| `MEMLY_PORT` | — | `3800` | HTTP transport port (`--http` mode only) |
+
+---
 
-## Self-Hosted (VPS)
+## Self-Hosted
 
-Run alongside your Memly proxy for zero-latency:
+Run alongside your Memly proxy on your VPS for zero-latency:
 
 ```bash
 MEMLY_API_KEY=memly_... bun run packages/mcp-server/src/index.ts --http

package/dist/index.js

@@ -20299,6 +20299,43 @@ ${MEMLY_INSTRUCTION_BLOCK}
 `);
   return { ide: "Windsurf", file: filePath, status: "created" };
 }
+function writeJetBrains(projectRoot) {
+  const ideaDir = join(projectRoot, ".idea");
+  if (!existsSync(ideaDir))
+    return null;
+  const filePath = join(ideaDir, "mcp.json");
+  const MARKER = '"memly"';
+  if (existsSync(filePath)) {
+    const existing = readFileSync(filePath, "utf-8");
+    if (existing.includes(MARKER)) {
+      return { ide: "JetBrains", file: filePath, status: "skipped" };
+    }
+    try {
+      const config2 = JSON.parse(existing);
+      config2.servers = config2.servers ?? {};
+      config2.servers["memly"] = {
+        command: "npx",
+        args: ["-y", "@memly/mcp-server"],
+        env: { MEMLY_API_KEY: "<your-memly-api-key>" }
+      };
+      writeFileSync(filePath, JSON.stringify(config2, null, 2));
+      return { ide: "JetBrains", file: filePath, status: "updated" };
+    } catch {
+      return null;
+    }
+  }
+  mkdirSync(ideaDir, { recursive: true });
+  writeFileSync(filePath, JSON.stringify({
+    servers: {
+      memly: {
+        command: "npx",
+        args: ["-y", "@memly/mcp-server"],
+        env: { MEMLY_API_KEY: "<your-memly-api-key>" }
+      }
+    }
+  }, null, 2));
+  return { ide: "JetBrains", file: filePath, status: "created" };
+}
 function writeClaudeDesktop() {
   const os = platform();
   let configPath;
@@ -20347,6 +20384,9 @@ function runInit() {
   const claudeResult = writeClaudeDesktop();
   if (claudeResult)
     results.push(claudeResult);
+  const jetbrainsResult = writeJetBrains(projectRoot);
+  if (jetbrainsResult)
+    results.push(jetbrainsResult);
   const icons = {
     created: "✅",
     updated: "✅",
@@ -20371,7 +20411,7 @@ function runInit() {
 
 // src/index.ts
 var apiKey = process.env.MEMLY_API_KEY;
-if (process.argv.includes("--init")) {
+if (process.argv.includes("--init") || process.argv.includes("init")) {
   runInit();
   process.exit(0);
 }

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@memly/mcp-server",
-    "version": "0.2.0",
+    "version": "0.2.2",
     "description": "Memly MCP Server — persistent memory for any IDE",
     "type": "module",
     "main": "dist/index.js",