@more-md/mcp-memory 0.1.0 → 0.1.1

package/README.md

@@ -1,40 +1,39 @@
 # @more-md/mcp-memory
 
-Portable long-term memory for AI assistants — as an **MCP server**.
+Portable long-term memory for AI assistants, as an MCP server.
 
-Connect it once and your assistant can remember things across chats, and the
-same memory follows you from Claude to Cursor to any other MCP-capable
-assistant. You hold the key (a short PIN); the memory is encrypted at rest and
-lives at a URL you control ([mem.more.md](https://mem.more.md)).
+Connect it once and your assistant remembers things across chats. The same
+memory follows you from Claude to Cursor to any other MCP-capable client. You
+hold the key, a short PIN. The memory is encrypted at rest and lives at a URL
+you control, [mem.more.md](https://mem.more.md).
 
-## Why an MCP server (and not "just give the AI a URL")?
+## Why an MCP server
 
-Telling a chat model to *"fetch this URL and use it as your memory"* is the
-exact shape of a prompt‑injection attack — a web page telling the assistant to
-persist your data somewhere. Well‑aligned models refuse it, and they're right
-to.
+Telling a chat model to "fetch this URL and use it as your memory" looks exactly
+like a prompt-injection attack: a web page instructing the assistant to persist
+your data somewhere. Well-aligned models refuse it, and they should.
 
-An MCP server flips that around:
+An MCP server works the other way around:
 
-- **You** add this server to your assistant's config (with your memory URL +
-  PIN). That explicit, user‑performed connection is the authorization.
-- The assistant calls **typed tools** (`remember`, `recall`) — it never treats
-  a fetched web page as instructions.
-- Every call is HTTPS, authed with your PIN. Your data goes only to the memory
-  URL you configured.
+- You add this server to your assistant's config, with your memory URL and PIN.
+  You set that connection up by hand, and that is the authorization.
+- The assistant calls typed tools (`remember`, `recall`). It never treats a
+  fetched web page as instructions.
+- Every call runs over HTTPS and is authed with your PIN. Your data goes only to
+  the memory URL you configured.
 
-## Get your memory URL + PIN
+## Get your memory URL and PIN
 
-Visit **https://mem.more.md** (or ask any assistant that already minted a
-session for you). You'll get a URL like `https://mem.more.md/AbC12xyz` and a
-4‑digit PIN. Keep them — that pair is your portable memory.
+Visit [mem.more.md](https://mem.more.md), or ask any assistant that already
+minted a session for you. You get a URL like `https://mem.more.md/AbC12xyz` and
+a 4-digit PIN. Keep the pair. That is your portable memory.
 
 ## Connect it
 
-### Claude Desktop / Claude Code / Cursor (and most MCP clients)
+### Claude Desktop, Claude Code, Cursor, and most MCP clients
 
 Add this to your MCP config (`claude_desktop_config.json`, `.cursor/mcp.json`,
-`.mcp.json`, …). Once published to npm:
+`.mcp.json`). This uses the published npm package:
 
 ```json
 {
@@ -51,7 +50,7 @@ Add this to your MCP config (`claude_desktop_config.json`, `.cursor/mcp.json`,
 }
 ```
 
-Running from a local checkout instead:
+To run from a local checkout instead:
 
 ```json
 {
@@ -65,33 +64,33 @@ Running from a local checkout instead:
 }
 ```
 
-Restart the client. You'll see a `memory` server with three tools.
+Restart the client. A `memory` server shows up with three tools.
 
 ## Tools
 
 | Tool | What it does |
 |------|--------------|
-| `remember` | Save a memory (`title`, `body`, `memory_type`: episodic/semantic, `importance` 1‑10). |
+| `remember` | Save a memory (`title`, `body`, `memory_type`: episodic or semantic, `importance` 1 to 10). |
 | `recall` | Search your memory by keyword or meaning before answering about the past. |
 | `recall_day` | Read everything saved on a given calendar day. |
 
-The assistant decides when to call these — a good one saves durable facts
-(your name, preferences, projects) as `semantic` and checks `recall` before
-answering questions about earlier context. You can always tell it to save or
-forget something specific.
+The assistant decides when to call these. A good one saves durable facts (your
+name, preferences, projects) as `semantic` and checks `recall` before answering
+questions about earlier context. You can always tell it to save or forget
+something specific.
 
 ## Privacy
 
-- Encrypted at rest; reachable only with your PIN.
-- Export or delete everything anytime (`/export`, delete tools/endpoints).
+- Encrypted at rest, reachable only with your PIN.
+- Export or delete everything anytime (`/export`, delete tools and endpoints).
 - Open source. Nothing is stored that you didn't ask for.
 
 ## Develop
 
 ```bash
 npm install
-npm run build      # → dist/
-npm test           # unit tests (mocked fetch)
+npm run build      # builds dist/
+npm test           # unit tests with mocked fetch
 ```
 
 MIT © more.md

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@more-md/mcp-memory",
-    "version": "0.1.0",
+    "version": "0.1.1",
     "description": "Portable long-term memory for AI assistants, as an MCP server. Connect Claude Desktop, Cursor, or any MCP client to a mem.more.md memory the user controls.",
     "type": "module",
     "bin": {
@@ -38,7 +38,7 @@
     "homepage": "https://mem.more.md",
     "repository": {
         "type": "git",
-        "url": "https://github.com/more-md/monorepo.git",
+        "url": "git+https://github.com/more-md/monorepo.git",
         "directory": "packages/mcp-memory"
     },
     "dependencies": {