From d7c183b3e17f68c7777d93b83a6104bb194aa082 Mon Sep 17 00:00:00 2001
From: Alex Newman <thedotmack@gmail.com>
Date: Sun, 28 Dec 2025 22:55:05 -0500
Subject: [PATCH] fix: rename 'mem-search' to 'mcp-search' for consistency
 across documentation and configuration

---
 docs/public/usage/claude-desktop.mdx |  8 ++++----
 plugin/.mcp.json                     |  2 +-
 plugin/package.json                  |  2 +-
 plugin/skills/mem-search/SKILL.md    | 27 +++++++++++++++++++++++++++
 src/servers/mcp-server.ts            |  2 +-
 5 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/docs/public/usage/claude-desktop.mdx b/docs/public/usage/claude-desktop.mdx
index 8c261cd3..f04160bb 100644
--- a/docs/public/usage/claude-desktop.mdx
+++ b/docs/public/usage/claude-desktop.mdx
@@ -17,7 +17,7 @@ Claude Desktop can access your claude-mem memory database through the **mem-sear
 Before installing the skill, ensure:
 
 1. **claude-mem is installed** and the worker service is running
-2. **MCP server is configured** in Claude Desktop (the skill uses the `mem-search` MCP server)
+2. **MCP server is configured** in Claude Desktop (the skill uses the `mcp-search` MCP server)
 
 ### Verify Worker is Running
 
@@ -52,7 +52,7 @@ npm run build  # Generates plugin/skills/mem-search.zip
 
 ### Step 3: Configure MCP Server
 
-The skill requires the `mem-search` MCP server. Add this to your Claude Desktop configuration:
+The skill requires the `mcp-search` MCP server. Add this to your Claude Desktop configuration:
 
 <Tabs>
   <Tab title="macOS">
@@ -61,7 +61,7 @@ The skill requires the `mem-search` MCP server. Add this to your Claude Desktop
     ```json
     {
       "mcpServers": {
-        "mem-search": {
+        "mcp-search": {
           "command": "node",
           "args": [
             "/Users/YOUR_USERNAME/.claude/plugins/marketplaces/thedotmack/plugin/scripts/mcp-server.cjs"
@@ -77,7 +77,7 @@ The skill requires the `mem-search` MCP server. Add this to your Claude Desktop
     ```json
     {
       "mcpServers": {
-        "mem-search": {
+        "mcp-search": {
           "command": "node",
           "args": [
             "C:\\Users\\YOUR_USERNAME\\.claude\\plugins\\marketplaces\\thedotmack\\plugin\\scripts\\mcp-server.cjs"
diff --git a/plugin/.mcp.json b/plugin/.mcp.json
index 7fb56e4a..e79e1d5e 100644
--- a/plugin/.mcp.json
+++ b/plugin/.mcp.json
@@ -1,6 +1,6 @@
 {
   "mcpServers": {
-    "mem-search": {
+    "mcp-search": {
       "type": "stdio",
       "command": "${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server.cjs"
     }
diff --git a/plugin/package.json b/plugin/package.json
index d6ff4bc2..9e4924e7 100644
--- a/plugin/package.json
+++ b/plugin/package.json
@@ -1,6 +1,6 @@
 {
   "name": "claude-mem-plugin",
-  "version": "8.2.5",
+  "version": "8.2.6",
   "private": true,
   "description": "Runtime dependencies for claude-mem bundled hooks",
   "type": "module",
diff --git a/plugin/skills/mem-search/SKILL.md b/plugin/skills/mem-search/SKILL.md
index 750d839d..61aa0fa6 100644
--- a/plugin/skills/mem-search/SKILL.md
+++ b/plugin/skills/mem-search/SKILL.md
@@ -3,6 +3,33 @@ name: mem-search
 description: Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
 ---
 
+<!-- TL;DR - Essential Workflow -->
+## Quick Reference
+
+**The 3-Layer Pattern (ALWAYS follow this):**
+
+1. **Search** - Get index of results with IDs
+   ```
+   search(query="...", limit=20, project="...")
+   ```
+   Returns: Table with IDs, titles, dates (~50-100 tokens/result)
+
+2. **Timeline** - Get context around interesting results
+   ```
+   timeline(anchor=<ID>, depth_before=3, depth_after=3, project="...")
+   ```
+   Returns: Chronological context showing what was happening
+
+3. **Fetch** - Get full details ONLY for relevant IDs
+   ```
+   get_observations(ids=[...])  # ALWAYS batch for 2+ items
+   ```
+   Returns: Complete details (~500-1000 tokens/result)
+
+**Why:** 10x token savings. Never fetch full details without filtering first.
+
+---
+
 # Memory Search
 
 Search past work across all sessions. Simple workflow: search → get IDs → fetch details by ID.
diff --git a/src/servers/mcp-server.ts b/src/servers/mcp-server.ts
index a2b96c99..b2666561 100644
--- a/src/servers/mcp-server.ts
+++ b/src/servers/mcp-server.ts
@@ -435,7 +435,7 @@ const tools = [
 // Create the MCP server
 const server = new Server(
   {
-    name: 'mem-search-server',
+    name: 'mcp-search-server',
     version: '1.0.0',
   },
   {