Modal
CommunityPopularModal MCP server for serverless cloud compute. Run Python functions, train models, and deploy GPU workloads from AI assistants via Modal's sandboxed infrastructure.
| Publisher | modal-labs |
| Repository | modal-mcp |
| Language | TypeScript |
| Forks | 0 |
| Stars | 2.6K |
| Available tools | 18 |
| Transport type | stdio |
| Categories | |
| License | MIT |
| Links |
- Connect tools to AI workflows
Modal exposes MCP capabilities that can be used by compatible AI clients and agents.
- 18 available tools
Browse the callable actions below, including names and descriptions when provided by the server.
- Ready-to-copy setup
Use the installation snippets to configure this server in your preferred MCP client.
- Open source signals
2.6K stars and 0 forks from the linked repository.
Installation
Node.js 18+
{
"mcpServers": {
"modal": {
"command": "npx",
"args": [
"-y",
"@modal/mcp"
],
"env": {
"MODAL_TOKEN_ID": "<YOUR_TOKEN_ID>",
"MODAL_TOKEN_SECRET": "<YOUR_TOKEN_SECRET>"
}
}
}
}Available Tools
- list_functions
List all deployed functions in the Modal workspace
- create_function
Create and deploy a new serverless Python function to Modal
- update_function
Update an existing function's code or configuration
- delete_function
Remove a function from Modal deployment
- invoke_function
Execute a deployed function with specified parameters
- get_function_logs
Retrieve execution logs for a specific function
- list_apps
List all Modal apps in the workspace
- create_app
Create a new Modal app container
- deploy_app
Deploy an app with multiple functions to Modal
- get_app_status
Check the deployment status and health of an app
- create_gpu_job
Submit a GPU-accelerated job for model training or inference
- list_gpu_jobs
List all running and completed GPU jobs
- cancel_job
Cancel a running job or function execution
- get_job_metrics
Retrieve performance metrics and resource usage for jobs
- create_volume
Create a persistent storage volume for data sharing
- list_volumes
List all created storage volumes
- upload_files
Upload files to Modal storage or volumes
- get_billing_usage
Retrieve current billing and resource usage statistics
Use Modal MCP with multiple AI models
TypingMind connects MCP tools at the workspace level, so once Modal is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.
Setup guide to use the local connector
Use this when the MCP server needs access to local files, apps, or private resources on your computer.
Open the MCP settings
In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.
- Open TypingMind in your browser.
- Click the Settings icon.
- Go to Advanced Settings.
- Open the Model Context Protocol section.
- Click Setup Connector and choose This Device.
Run the connector command
Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.
- Copy the setup command shown by TypingMind.
- Open Terminal on macOS or Windows Terminal on Windows.
- Paste and run the command.
- Approve the package install if Terminal asks you to proceed.
- Keep the Terminal window running while using MCP tools.
Add Modal as a server
When the connector status is Ready, click Edit Servers and paste the MCP server configuration.
- Wait until the connector status shows Ready.
- Click Edit Servers.
- Paste the Modal MCP server configuration.
- Save the server list.
- Refresh if you want to confirm the connector is still ready.
{
"mcpServers": {
"modal": {
"command": "npx",
"args": [
"-y",
"@modal/mcp"
]
}
}
}Use it across models
Save the server list, open Plugins, enable the Modal MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.
- Open the Plugins page in TypingMind.
- Enable the Modal MCP tools.
- Start a chat and choose the AI model you want to use.
- Use the MCP tools in chat or assign them to an AI agent.
- Switch to another AI model whenever needed without reconnecting MCP.
Here is what I found using Modal.
Frequently asked questions
What is the Modal MCP server used for?
Modal is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.
Can I use Modal MCP with multiple AI models in TypingMind?
Yes. TypingMind connects MCP tools at the workspace level, so you can use Modal with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.
Why use Modal MCP with TypingMind?
TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Modal connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.
How do I connect Modal MCP to TypingMind?
Modal runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.
What tools does Modal MCP provide in TypingMind?
Modal exposes 18 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.
Do I need to share my API keys with TypingMind to use Modal MCP?
No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Modal requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.
Related MCP Servers
View all
Google GenAI Toolbox
MCP Toolbox for Databases is an open source MCP server for databases.
Firebase
The Firebase Command Line Tools
Google Kubernetes Engine (GKE)
Google 💚 MCP
Google Cloud Compute Engine
Google 💚 MCP
