Use when renaming symbols across files, finding all references to a function/class, moving code between files, or inlining variables — LSP-backed atomic multi-file refactoring
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
MCP server key: serena — tools: mcp__serena__*
Core principle: Type-aware, 100% recall. Grep finds strings; Serena finds symbols — including aliased imports, dynamic usages, and type-renamed references.
| Question | Use |
|---|---|
"Rename AuthService everywhere" | serena — rename_symbol |
"Find all callers of login()" | serena — find_references |
"Move UserMapper to another file" | serena — move_symbol |
"Inline the MAX_RETRIES constant" | serena — inline_symbol |
| "Find code about rate limiting" | cocoindex-code — semantic meaning |
| "Who calls AuthService in the graph?" | codebase-memory-mcp — architecture overview |
| "Is renaming this safe to ship?" | code-review-graph — blast radius |
mcp__serena__find_symbol(name, type?) — find by name/type (LSP, not grep)
mcp__serena__find_references(symbol) — all usages across the project
mcp__serena__get_symbol_info(symbol) — signature, docstring, defined-in, refs
mcp__serena__rename_symbol(symbol, new_name) — rename everywhere atomically
mcp__serena__move_symbol(symbol, target_file) — move + fix all imports
mcp__serena__replace_symbol_body(symbol, body) — replace impl, keep signature
mcp__serena__inline_symbol(symbol) — inline at all call sites
mcp__serena__get_call_graph(symbol) — call graph from a symbol
Rename across codebase:
1. mcp__serena__find_symbol("OldName") → confirm it's the right symbol
2. mcp__serena__find_references("OldName") → verify scope
3. mcp__serena__rename_symbol("OldName", "NewName") → atomic rename
Move a class to another file:
1. mcp__serena__get_symbol_info("MyClass") → see current location and imports
2. mcp__serena__move_symbol("MyClass", "src/new_module.py")
Find all callers before deleting:
1. mcp__serena__find_references("legacyFunction") → if empty, safe to delete
.serena/project.yml (committed to repo) controls which language servers are active:
languages:
- python
- typescript
- javascript
Language servers are auto-installed by serena on first use (pyright, typescript-language-server).
Low — on-demand per MCP call. No background indexing process. LSP server initializes on first call (~2-3s), then fast.
codebase-memory-mcp (Cypher graph, whole-codebase view)cocoindex-code (find code by meaning when you don't know exact names)code-review-graph (blast radius, safety score before PR)Grep tool (faster for literal strings with no aliasing concern)まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Route a codebase question to the right tool — structural graph, semantic search, or risk analysis. Use when you need to find or understand code without knowing exact file names.
日本語の概要は準備中です。原文の説明を表示しています。
Auto-configure CLAUDE.md and claude/ knowledge docs for a new project. Use when setting up Brain Bootstrap in a new repository. Discovers the codebase, fills in templates, and writes project-specific configuration.
日本語の概要は準備中です。原文の説明を表示しています。
Use before any new feature, component, or behavioral change — when you need to explore requirements and design before writing code
日本語の概要は準備中です。原文の説明を表示しています。
Activate safety guards for the session. Use /careful before critical operations — blocks rm -rf, DROP TABLE, git push --force, kubectl delete namespace, docker system prune via PreToolUse hook.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a user-facing changelog from git commits — categorize, filter noise, translate to user language. Runs in isolated fork context.
日本語の概要は準備中です。原文の説明を表示しています。
Save session state before context gets full or before ending. Writes current task state, branch, and loaded docs to claude/tasks/todo.md so the next session can resume cleanly.
日本語の概要は準備中です。原文の説明を表示しています。