docs(tools): update mcp-server docs for project_dir and create-project

- Server can now start from any directory, not just a valid project dir
- Document project_dir argument available on all tools
- Add create-project tool to the list of available tools

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Marek Fiala
2026-06-09 14:02:43 +02:00
committed by BOT
parent 12ea480988
commit 33924459ab

View File

@@ -317,7 +317,7 @@ To use the MCP server with an AI assistant, configure your agent or IDE to start
eim run "idf.py mcp-server"
2. Using ``idf.py`` directly: Run the MCP server with ``idf.py mcp-server`` from a shell where the ESP-IDF environment is already activated. The command must be executed from a valid ESP-IDF project directory, or use ``idf.py -C <project_dir> mcp-server`` to specify the project.
2. Using ``idf.py`` directly: Run the MCP server with ``idf.py mcp-server`` from a shell where the ESP-IDF environment is already activated. The server can be started from any directory. Use ``idf.py -C <project_dir> mcp-server`` or set the ``IDF_MCP_WORKSPACE_FOLDER`` environment variable to configure a default project. If no project is configured at startup, pass project directory explicitly in each tool call.
.. code-block:: bash
@@ -330,12 +330,15 @@ To use the MCP server with an AI assistant, configure your agent or IDE to start
Available Tools and Resources
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The MCP server provides the following commands you can use:
The MCP server provides the following tools:
- ``set target``: Set the ESP-IDF target (esp32, esp32s3, esp32c6, etc.)
- ``build project``: Build the ESP-IDF project with the current target
- ``flash project``: Flash the built project to a connected device. Specify it by port name.
- ``clean project``: Clean build artifacts
- ``create project``: Create a new ESP-IDF project from the sample template. Can be used before any project exists.
All tools accept an optional ``project_dir`` argument. When omitted, the tool operates on the directory configured at startup (``-C`` flag or ``IDF_MCP_WORKSPACE_FOLDER``). You can instruct the AI model to use a specific project directory explicitly, for example when working with multiple projects or when no default project was configured at startup.
The MCP server also provides these resources: