NebulaBlock API MCP
This repository hosts the official NebulaBlock API Model Context Protocol (MCP) server. This server integrates with the fastmcp library to expose the full range of NebulaBlock API functionalities as accessible tools, enabling seamless and efficient interaction within any MCP-compatible environment.
Project Structure
.
├── src/
│ ├── __init__.py
│ ├── config.py
│ ├── main.py
│ ├── tools.py
│ └── mcp_project.egg-info/
├── tests/
│ ├── __init__.py
│ └── test_main.py
├── scripts/
├── docs/
├── .env.example
├── .gitignore
├── pyproject.toml
├── README.md
└── uv.lock
src/: Contains the main application source code, including configuration and tool definitions.tests/: Contains unit and integration tests.scripts/: Reserved for utility scripts (e.g., setup, data generation).docs/: Reserved for supplementary documentation..env.example: Example file for environment variables..gitignore: Specifies intentionally untracked files to ignore.pyproject.toml: Project metadata and build system configuration, including dependencies and project information.README.md: This documentation file.uv.lock: Lock file foruvdependency management.
Installation and Setup
To set up and run this project, follow these steps:
-
Clone the repository (if applicable):
git clone https://github.com/Nebula-Block-Data/api-mcp cd mcp-project -
Create a virtual environment: It's highly recommended to use a virtual environment to manage project dependencies.
python3 -m venv .venv -
Activate the virtual environment:
- macOS/Linux:
source .venv/bin/activate
- Install dependencies:
This project uses
pyproject.tomlfor dependency management. Installsetuptoolsand then the project in editable mode.
This will installuv pip install -e .fastmcpand any other dependencies specified inpyproject.toml.
Running the NebulaBlock API MCP Server
To start the NebulaBlock API MCP server:
uv run -m src.main
You should see output similar to: [05/29/25 17:32:58] INFO Starting MCP server 'FastMCP' with transport 'stdio'
Configuring API Key
The NebulaBlock API key can be configured in two ways:
-
Using the
--api-keycommand-line argument: You can provide the API key directly when running the application:python -m src.main --api-key your_nebula_block_api_keyThis method will override any API key set in the
.envfile. -
Using a
.envfile: Create a file named.envin the root directory of the project and add your API key to it:NEBULA_BLOCK_API_KEY=your_nebula_block_api_keyThe application will automatically load the API key from this file if the
--api-keyargument is not provided.
Running Tests
To run the unit tests, ensure your virtual environment is activated and pytest is installed (it will be installed with pip install -e .):
pytest
You should see output indicating that the tests passed.
Integrating with an MCP Client
To utilize the NebulaBlock API MCP server, you need to configure your MCP client (e.g., VS Code with an MCP extension) to connect to this server. Below is an example configuration for a settings.json file:
{
"mcpServers": {
"nebula": {
"command": "~/path/to/uv",
"args": [
"--directory",
"~/path/to/nebulablock_mcp",
"run",
"-m",
"src.main",
"--api-key=YOUR_API_KEY"
]
}
}
}
- Replace
~/path/to/uvwith the actual path to youruvexecutable. - Replace
~/path/to/nebulablock_mcpwith the actual path to your project directory. - Replace
YOUR_API_KEYwith your actual NebulaBlock API key.
License
This project is licensed under the MIT License. See the LICENSE file (if created) for details.