RELATED 01
Memtrace
OFFICIAL SERVERLocal code graph with symbol history that coding agents query for search, impact and change tracking
511GitHub stars
1.6k/wknpm downloads
73popularity score
Serena
Gives a coding assistant IDE-like tools: find symbols and references, edit and refactor code by symbol.
By Oraios AI Python Local · stdio Developer tools
101 popularity score ★ 31k ↓ 148k/mo
What it does
Serena is a coding toolkit served over MCP that gives an assistant capabilities similar to an IDE. Instead of reading whole files and editing by line numbers, the assistant works with symbols: find a symbol, get a file's outline, find references, declarations and implementations, read diagnostics, replace a function's body, insert code before or after a symbol, rename and safely delete symbols. It also keeps project memories in markdown for long-running work and can query other projects.
Two backends power it. By default it uses language servers (LSP) and supports over 40 languages, including Python, TypeScript, Java, C#, Go, Rust and C/C++. Alternatively the paid Serena JetBrains plugin uses a JetBrains IDE's own analysis, adding moves, inlining, type hierarchy, inspections and an interactive debugger. Basic file, search and shell tools are included but are usually switched off when the client already has them.
The docs say to install it with uv (uv tool install -p 3.13 serena-agent), run serena init, then configure the client to launch serena start-mcp-server (with a context such as claude-code and a project); it can also run in HTTP mode. The docs warn against installing it from MCP or plugin marketplaces because their commands are outdated. Behaviour is configured in YAML per project, client context and mode.
Tools 42
find_symbol- Performs a global (or local) search for symbols using the language server backend.
get_symbols_overview- Gets an overview of the top-level symbols defined in a given file.
find_referencing_symbols- Finds symbols that reference the given symbol.
find_declaration- Finds the declaration/definition of a symbol.
find_implementations- Finds the implementations of a symbol.
get_diagnostics_for_file- Gets diagnostics for a file, grouped by symbol.
get_diagnostics_for_symbol- Gets diagnostics for a symbol and, optionally, for symbols that reference it.
replace_symbol_body- Replaces the full definition of a symbol using the language server backend.
insert_after_symbol- Inserts content after the end of the definition of a given symbol.
insert_before_symbol- Inserts content before the beginning of the definition of a given symbol.
rename_symbol- Renames a symbol throughout the codebase using language server refactoring capabilities.
safe_delete_symbol- Safely deletes a symbol.
restart_language_server- Restarts the language server(s).
jet_brains_find_symbol- Searches for symbols using the JetBrains backend.
jet_brains_find_referencing_symbols- Finds symbols that reference the given symbol using the JetBrains backend.
jet_brains_type_hierarchy- Retrieves the type hierarchy of a symbol using the JetBrains backend.
jet_brains_rename- Renames a symbol, file or directory throughout the codebase using the JetBrains backend.
jet_brains_move- Moves a symbol, file or directory, updating all references, using the JetBrains backend.
jet_brains_inline_symbol- Inlines a symbol, replacing all call sites with its body, using the JetBrains backend.
jet_brains_safe_delete- Safely deletes a symbol after checking for remaining usages, using the JetBrains backend.
jet_brains_run_inspections- Runs JetBrains IDE inspections on a file and returns the results.
jet_brains_debug- Debugging via a persistent debug REPL connected to the JetBrains IDE.
search_for_pattern- Searches for a pattern in files.
replace_content- Replaces content in a file (optionally using regular expressions).
replace_in_files- Replaces occurrences of a pattern across multiple files, with dry-run preview.
read_file- Reads a file within the project directory.
create_text_file- Creates or overwrites a file in the project directory.
list_dir- Lists files and directories in the given directory.
find_file- Finds files in the given relative paths.
execute_shell_command- Executes a shell command.
activate_project- Activates a project based on the project name or path.
get_current_config- Prints the current configuration, including projects, tools, contexts and modes.
open_dashboard- Opens the Serena web dashboard in the default web browser.
list_memories- Lists available memories.
read_memory- Reads the content of a memory file.
write_memory- Writes information about the project to a memory in markdown for future tasks.
edit_memory- Replaces content matching a regular expression in a memory.
delete_memory- Deletes a memory file.
query_project- Queries an external project by running a read-only tool.
onboarding- Performs onboarding (identifying the project structure and essential tasks).
initial_instructions- Provides instructions on using Serena for clients that do not read them.
serena_repl- Executes Python code that accesses Serena's functionality programmatically.