brain-cache 0.1.0 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +15 -29
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -14,19 +14,7 @@ brain-cache is an MCP server that gives Claude local, indexed access to your cod
14
14
 
15
15
  ## Use inside Claude Code (MCP)
16
16
 
17
- The primary way to use brain-cache is as an MCP server. Once configured, Claude automatically calls brain-cache tools instead of reading raw files no prompting required.
18
-
19
- ```json
20
- // .claude/settings.json
21
- {
22
- "mcpServers": {
23
- "brain-cache": {
24
- "command": "brain-cache",
25
- "args": ["mcp"]
26
- }
27
- }
28
- }
29
- ```
17
+ The primary way to use brain-cache is as an MCP server. Run `brain-cache init` once it auto-configures `.mcp.json` in your project root so Claude Code connects immediately. No manual JSON setup needed.
30
18
 
31
19
  Claude then has access to:
32
20
 
@@ -99,26 +87,24 @@ brain-cache init
99
87
  brain-cache index
100
88
  ```
101
89
 
102
- `brain-cache init` appends MCP tool instructions to your `CLAUDE.md` so Claude knows when and how to prefer brain-cache tools over built-in file reading. Runs once; won’t duplicate.
103
-
104
- **Step 3: Add MCP server to Claude Code**
90
+ `brain-cache init` sets up your project: configures `.mcp.json` so Claude Code connects to brain-cache automatically, and appends MCP tool instructions to `CLAUDE.md`. Runs once; idempotent.
105
91
 
106
- ```json
107
- // .claude/settings.json
108
- {
109
- "mcpServers": {
110
- "brain-cache": {
111
- "command": "brain-cache",
112
- "args": ["mcp"]
113
- }
114
- }
115
- }
116
- ```
117
-
118
- **Step 4: Use Claude normally**
92
+ **Step 3: Use Claude normally**
119
93
 
120
94
  brain-cache tools are called automatically. You don’t change how you work — the context just gets better.
121
95
 
96
+ > **Advanced:** `init` creates `.mcp.json` automatically. If you need to customise it manually, the expected shape is:
97
+ > ```json
98
+ > {
99
+ > "mcpServers": {
100
+ > "brain-cache": {
101
+ > "command": "brain-cache",
102
+ > "args": ["mcp"]
103
+ > }
104
+ > }
105
+ > }
106
+ > ```
107
+
122
108
  ---
123
109
 
124
110
  ## 🧩 Core capabilities
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "brain-cache",
3
- "version": "0.1.0",
3
+ "version": "0.2.0",
4
4
  "description": "Local MCP-first context engine for Claude. Index your codebase, retrieve only what matters, and cut token usage.",
5
5
  "license": "MIT",
6
6
  "type": "module",