You can quickly spin up an MCP JetBrains server for a test Room environment and interact with it via a Meshagent-powered chatbot. Environment Variables Needed:
  • IDE_PORT=8090

​
Steps

  1. Install Meshagent CLI 
    pip install "meshagent[all]"
  2. Sign Up and Authenticate
    See CLI Getting Started for account creation and login.
  3. Start the MCP Server as an Agent in a Meshagent Room 
    meshagent service test --room=test --role=agent --image=meshagent/mcp-jetbrains:latest --env MESHAGENT_PORT=8001 --env IDE_PORT=8090 --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" --name=mcp-jetbrains-service-test
    • This command starts a Meshagent Room named test and attaches a JetBrains MCP server as a tool agent.
    • The Room and all its services are automatically closed when inactive, removing all related tools and chatbots.
  4. Join with a Chatbot That Can Use the JetBrains Toolkit 
    meshagent chatbot join --room=test --agent-name=mcp-jetbrains --name=mcp-jetbrains --toolkit=mcp-jetbrains
    • This launches a chatbot in the same Room, making the MCP JetBrains tools accessible via chat.
    • Multiple toolkits can be linked to the same agent concurrently.
    • A Room link will be displayed in the output.
  5. Try It Out
    • Open the Room link in your browser provided by Step 4.
    • Send a message to the agent chatbot to interact with JetBrains tools.

​
Project Level Deployment: Persistent Services for Every Room

For production scenarios and persistent tool access, you can deploy MCP server tools and a chatbot once per project—making them available in all Rooms under that project, without managing local processes.

​
Steps

  1. Create the MCP JetBrains Service (Agent) 
    meshagent service create --role=agent --image=meshagent/mcp-jetbrains:latest --env MESHAGENT_PORT=8001 --env IDE_PORT=8090 --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" --name=mcp-jetbrains-service
    • This ensures the JetBrains MCP server container is brought up automatically in any new Room.
  2. Create the Chatbot Service Linked to the MCP Tool 
    meshagent service create --image="meshagent/cli:latest" --port="num=9001 path=/agent liveness=/ type=meshagent.callable participant_name=mcp-jetbrains-chatbot" --env="MESHAGENT_PORT=9001" --name="mcp-jetbrains-chatbot-service" --command="meshagent chatbot service --agent-name=mcp-jetbrains-chatbot --toolkit=mcp-jetbrains"
    • This launches an AI chatbot service able to leverage the exposed JetBrains tools.
    • Both services are auto-provisioned for every new Room in your Meshagent project.

​
Tools Available

The JetBrains MCP Server provides an extensive suite of automation tools for JetBrains IDEs (IntelliJ, PyCharm, WebStorm, Android Studio, and more):
ToolShort Description
create_new_file_with_textCreates a new file at the specified path within the project directory and populates it with the provided text
execute_action_by_idExecutes an action by its ID in JetBrains IDE editor
execute_terminal_commandExecutes a specified shell command in the IDE’s integrated terminal
find_commit_by_messageSearches for a commit based on the provided text or keywords in the project history
find_files_by_name_substringSearches for all files in the project whose names contain the specified substring
get_all_open_file_pathsLists full path relative paths to project root of all currently open files
get_all_open_file_textsReturns text of all currently open files in the JetBrains IDE editor
get_debugger_breakpointsRetrieves a list of all line breakpoints currently set in the project
get_file_text_by_pathRetrieves the text content of a file using its path relative to project root
get_open_in_editor_file_pathRetrieves the absolute path of the currently active file
get_open_in_editor_file_textRetrieves the complete text content of the currently active file
get_progress_indicatorsRetrieves the status of all running progress indicators
get_project_dependenciesGet list of all dependencies defined in the project
get_project_modulesGet list of all modules in the project with their dependencies
get_project_vcs_statusRetrieves the current version control status of files in the project
get_run_configurationsReturns a list of run configurations for the current project
get_selected_in_editor_textRetrieves the currently selected text from the active editor
get_terminal_textRetrieves the current text content from the first active terminal
list_available_actionsLists all available actions in JetBrains IDE editor
list_directory_tree_in_folderProvides a hierarchical tree view of the project directory structure
list_files_in_folderLists all files and directories in the specified project folder
open_file_in_editorOpens the specified file in the JetBrains IDE editor
replace_current_file_textReplaces the entire content of the currently active file
replace_file_text_by_pathReplaces the entire content of a specified file with new text
replace_selected_textReplaces the currently selected text in the active editor
replace_specific_textReplaces specific text occurrences in a file with new text
run_configurationRun a specific run configuration in the current project
search_in_files_contentSearches for a text substring within all files in the project
toggle_debugger_breakpointToggles a debugger breakpoint at the specified line in a project file
waitWaits for a specified number of milliseconds

​
Tools Details

For further configuration and advanced usage, please consult the Meshagent CLI Documentation.
Learn more about the Model Context Protocol and its secure management using Docker here.