chore: remove @praha/byethrow MCP server, use documentation URL (#513)

ryoppippi · web-flow · commit ba87e3cbd91e · 2025-08-15T11:55:54.000+01:00
- Remove byethrow MCP server from .mcp.json

- Update CLAUDE.md to reference byethrow llms.txt documentation URL

- Keep @praha/byethrow package dependency for Result type usage
diff --git a/.mcp.json b/.mcp.json
@@ -14,15 +14,6 @@
 				"--no-cache"
 			]
 		},
-		"@praha/byethrow": {
-			"type": "stdio",
-			"command": "bun",
-			"args": [
-				"x",
-				"@praha/byethrow-mcp"
-			],
-			"env": {}
-		},
 		"lsmcp": {
 			"command": "bun",
 			"args": [
diff --git a/CLAUDE.md b/CLAUDE.md
@@ -170,6 +170,7 @@ This is a CLI tool that analyzes Claude Code usage data from local JSONL files s
 **Error Handling:**
 
 - **Prefer @praha/byethrow Result type** over traditional try-catch for functional error handling
+  - Documentation: https://praha-inc.github.io/byethrow/llms.txt
 - Use `Result.try()` for wrapping operations that may throw (JSON parsing, etc.)
 - Use `Result.isFailure()` for checking errors (more readable than `!Result.isSuccess()`)
 - Use early return pattern (`if (Result.isFailure(result)) continue;`) instead of ternary operators
