Serena
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_dirB | List files and directories. |
| replace_contentC | Replace pattern in file. |
| get_symbols_overviewB | Get symbols overview for a file. |
| find_symbolC | Search symbols by pattern. Returns locations. |
| find_referencing_symbolsB | Find references to symbol. Returns locations with snippets. |
| rename_symbolB | Rename symbol throughout codebase using LSP. |
| write_memoryC | Write memory to project store. |
| read_memoryC | Read memory. Only if relevant to current task. |
| list_memoriesB | List all memories. |
| delete_memoryC | Delete memory. Only on explicit user request. |
| edit_memoryC | Replace content in memory. |
| activate_projectC | Activate project. |
| switch_modesC | Activate modes like ['editing', 'interactive']. |
| check_onboarding_performedA | Check onboarding status. Call before starting work. |
| onboardingB | Call if onboarding not yet performed. |
| think_about_collected_informationA | Call after search sequences to assess completeness. |
| think_about_task_adherenceA | Call before code edits. |
| think_about_whether_you_are_doneC | Call when you think you're done. |
| initial_instructionsB | Get essential Serena usage instructions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools have distinct purposes, but there is some potential confusion between 'think_about_collected_information', 'think_about_task_adherence', and 'think_about_whether_you_are_done', as they all involve reflective 'think about' actions and could overlap in usage scenarios. The other tools are clearly differentiated by their specific functions.
The naming is mixed with no clear pattern: some use verb_noun (e.g., 'activate_project', 'delete_memory'), others use noun_verb (e.g., 'initial_instructions'), and some are descriptive phrases (e.g., 'think_about_collected_information'). While readable, this inconsistency can make it harder for agents to predict tool names.
With 19 tools, the count is on the higher side but reasonable for a comprehensive code and project management server like Serena. It covers a wide range of operations from file handling to memory management and reflective tasks, suggesting a well-scoped but extensive feature set.
The tool set provides complete coverage for the inferred domain of code editing, project management, and memory operations. It includes CRUD for memories (write, read, edit, delete, list), symbol handling (find, rename, overview), file operations (list, replace), project activation, onboarding, and reflective checks, leaving no obvious gaps for core workflows.