Browse
→ Infrastructure
→ Modal MCP
Modal MCP
Run serverless GPU and CPU workloads on Modal via MCP. Deploy functions, trigger jobs, and retrieve results — giving agents access to scalable compute without managing infrastructure.
MCP unverified
Integration
| Transport | stdio |
| Auth | api-key |
| Endpoint | uvx modal-mcp-server |
| Install | uvx modal-mcp-server |
Use Cases
| 01 | Run GPU-intensive ML jobs from an agent without provisioning servers |
| 02 | Deploy and invoke Python functions on Modal's serverless compute from agent workflows |
| 03 | Scale batch processing tasks dynamically based on agent-determined load |
Tags
modal serverless gpu compute ml python
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>