Add open_dashboard MCP tool for on-demand dashboard opening

This provides an alternative for users who want to disable automatic
browser opening (web_dashboard_open_on_launch: False) but still have
easy access to the dashboard through AI assistance.

Changes:
- Add OpenDashboardTool in config_tools.py
- Add open_dashboard() and get_dashboard_url() methods to SerenaAgent
- Store dashboard URL in _dashboard_url field
- Update documentation with new tool and configuration option
- Update config template comment to mention the tool

Closes #875
This commit is contained in:
Tomasz Wyderka committed 2025-12-28 03:44:07 +01:00
1 parent c569212ec6
commit 511ad0542b
5 files changed
+54 -1

No files matched your search

+1
View File
@@ -28,6 +28,7 @@ Note that in most configurations, only a subset of these tools will be enabled s
* `list_dir`: Lists files and directories in the given directory (optionally with recursion).
* `list_memories`: Lists memories in Serena's project-specific memory store.
* `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
* `open_dashboard`: Opens the Serena web dashboard in the default web browser.
* `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with th
e necessary context).
* `read_file`: Reads a file within the project directory.
+9
View File
@@ -20,3 +20,12 @@ Serena comes with built-in tools for monitoring and managing the current session
Both can be configured in Serena's [configuration](050_configuration) file (`serena_config.yml`).
If enabled, they will automatically be opened as soon as the Serena agent/MCP server is started.
## Disabling Automatic Browser Opening
If you prefer not to have the dashboard open automatically (e.g., to avoid focus stealing), you can disable it
by setting `web_dashboard_open_on_launch: False` in your `serena_config.yml`.
When automatic opening is disabled, you can still access the dashboard by:
* Navigating directly to `http://localhost:24282/dashboard/index.html` in your browser
* Asking the AI to use the `open_dashboard` tool, which will open the dashboard in your default browser