Modal MCP Server
local-only server
The server can only run on the client’s local machine because it depends on local resources.
Integrations
Serves as the API framework for the MCP server, providing documentation at /docs endpoint and RESTful endpoints for tool invocation.
Provides repository access for the MCP server code, supporting installation via git clone from a GitHub repository.
Provides tools for deploying and running Modal applications in the cloud, allowing AI agents to deploy Modal apps and execute functions within Modal applications.
Modal MCP Server
An MCP server implementation for interacting with Modal volumes and deploying Modal applications from within Cursor.
Installation
- Clone this repository:
- Install dependencies using
uv
:
Configuration
To use this MCP server in Cursor, add the following configuration to your ~/.cursor/mcp.json
:
Replace /path/to/modal-mcp-server
with the absolute path to your cloned repository.
Requirements
- Python 3.11 or higher
uv
package manager- Modal CLI configured with valid credentials
- For Modal deploy support:
- Project being deployed must use
uv
for dependency management - Modal must be installed in the project's virtual environment
- Project being deployed must use
Supported Tools
Modal Volume Operations
- List Modal Volumes (
list_modal_volumes
)- Lists all Modal volumes in your environment
- Returns JSON-formatted volume information
- Parameters: None
- List Volume Contents (
list_modal_volume_contents
)- Lists files and directories in a Modal volume
- Parameters:
volume_name
: Name of the Modal volumepath
: Path within volume (default: "/")
- Copy Files (
copy_modal_volume_files
)- Copies files within a Modal volume
- Parameters:
volume_name
: Name of the Modal volumepaths
: List of paths where last path is destination
- Example:
["source.txt", "dest.txt"]
or["file1.txt", "file2.txt", "dest_dir/"]
- Remove Files (
remove_modal_volume_file
)- Deletes a file or directory from a Modal volume
- Parameters:
volume_name
: Name of the Modal volumeremote_path
: Path to file/directory to deleterecursive
: Boolean flag for recursive deletion (default: false)
- Upload Files (
put_modal_volume_file
)- Uploads a file or directory to a Modal volume
- Parameters:
volume_name
: Name of the Modal volumelocal_path
: Path to local file/directory to uploadremote_path
: Path in volume to upload to (default: "/")force
: Boolean flag to overwrite existing files (default: false)
- Download Files (
get_modal_volume_file
)- Downloads files from a Modal volume
- Parameters:
volume_name
: Name of the Modal volumeremote_path
: Path to file/directory in volume to downloadlocal_destination
: Local path to save downloaded files (default: current directory)force
: Boolean flag to overwrite existing files (default: false)
- Note: Use "-" as
local_destination
to write file contents to stdout
Modal Deployment
- Deploy Modal App (
deploy_modal_app
)- Deploys a Modal application
- Parameters:
absolute_path_to_app
: Absolute path to the Modal application file
- Note: The project containing the Modal app must:
- Use
uv
for dependency management - Have the
modal
CLI installed in its virtual environment
- Use
Response Format
All tools return responses in a standardized format, with slight variations depending on the operation type:
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be installed
An MCP server that enables AI agents to interact with Modal, allowing them to deploy apps and run functions in a serverless cloud environment.