mcp-automl 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

{mcp_automl-0.1.1.dist-info → mcp_automl-0.1.3.dist-info}/METADATA

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: mcp-automl
-Version: 0.1.1
+Version: 0.1.3
 Summary: MCP server for end-to-end machine learning
 Author-email: ke <idea7766@gmail.com>
 License-File: LICENSE
-Requires-Python: >=3.11
+Requires-Python: <3.12,>=3.10
 Requires-Dist: duckdb>=1.4.3
 Requires-Dist: joblib<1.4
 Requires-Dist: mcp>=1.21.2
@@ -39,12 +39,26 @@ Add to your MCP client configuration (e.g., Claude Desktop, Gemini CLI, Cursor,
   "mcpServers": {
     "mcp-automl": {
       "command": "uvx",
-      "args": ["--from", "git+https://github.com/idea7766/mcp-automl", "mcp-automl"]
+      "args": ["--python", "3.11", "mcp-automl"]
     }
   }
 }
 ```
 
+**Or using Docker:**
+
+```json
+{
+  "mcpServers": {
+    "mcp-automl": {
+      "command": "docker",
+      "args": ["run", "-i", "--rm", "-v", "${PWD}:/workspace", "-v", "${HOME}/.mcp-automl:/root/.mcp-automl", "idea7766/mcp-automl:latest"]
+    }
+  }
+}
+```
+
+
 ### Available Tools
 
 | Tool | Description |
@@ -67,16 +81,18 @@ MCP AutoML includes an **data science workflow skill** that guides AI agents thr
 
 ### Installing the Skill
 
-Copy the skill directory to your agent's skill folder:
+**For Gemini CLI:**
 
 ```bash
-# For Gemini Code Assist
-cp -r skill/data-science-workflow ~/.gemini/skills/
+gemini skills install https://github.com/idea7766/mcp-automl --path skill/data-science-workflow
+```
 
-# For Claude Code
-cp -r skill/data-science-workflow ~/.claude/skills/
+**For Claude Code:**
 
-# For other agents, copy to their respective skill directories
+```bash
+# Clone the repo and copy the skill
+git clone https://github.com/idea7766/mcp-automl.git
+cp -r mcp-automl/skill/data-science-workflow ~/.claude/skills/
 ```
 
 The skill file is located at `skill/data-science-workflow/SKILL.md`.
@@ -84,6 +100,17 @@ The skill file is located at `skill/data-science-workflow/SKILL.md`.
 ## Configuration
 
 Models and experiments are saved to `~/.mcp-automl/experiments/` by default.
+## Troubleshooting
+
+### macOS: LightGBM OpenMP Error
+
+If you encounter an error like `Library not loaded: @rpath/libomp.dylib`, you need to install OpenMP:
+
+```bash
+brew install libomp
+```
+
+This is a system-level dependency required by LightGBM on macOS. Linux and Windows users typically don't need this step.
 
 ## Dependencies
 

{mcp_automl-0.1.1.dist-info → mcp_automl-0.1.3.dist-info}/RECORD

@@ -1,8 +1,8 @@
 mcp_automl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_automl/__main__.py,sha256=ncTRY5zgcNOS7JcLnCVhPd9KsxjyREC245P2eo33BuI,74
 mcp_automl/server.py,sha256=rk8mQFSm-Y-p5-6DqvPkdiUN6WQrC7jXGXTb4Byedgw,42435
-mcp_automl-0.1.1.dist-info/METADATA,sha256=UKa51AqkUr0J14f3-emm1GqXYHHHhF8HtQ2wa1Gi-gM,3066
-mcp_automl-0.1.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-mcp_automl-0.1.1.dist-info/entry_points.txt,sha256=7QuAE_HatGpFE7Ul7hqNHmpaMf0Ug86aFkaCXofjhLg,54
-mcp_automl-0.1.1.dist-info/licenses/LICENSE,sha256=MLSjoBTdoZnIBt__JNue8D2KnKqNg7Mt_LYWn9vNNws,1065
-mcp_automl-0.1.1.dist-info/RECORD,,
+mcp_automl-0.1.3.dist-info/METADATA,sha256=8ijC0ds1x0633RNb3yAtRVBTGXfVBxNhQQsX5v2qUWA,3638
+mcp_automl-0.1.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+mcp_automl-0.1.3.dist-info/entry_points.txt,sha256=7QuAE_HatGpFE7Ul7hqNHmpaMf0Ug86aFkaCXofjhLg,54
+mcp_automl-0.1.3.dist-info/licenses/LICENSE,sha256=MLSjoBTdoZnIBt__JNue8D2KnKqNg7Mt_LYWn9vNNws,1065
+mcp_automl-0.1.3.dist-info/RECORD,,