# pi-modal-mcp

> pi-modal-mcp — salus-ryan-pi-modal-mcp. Use this tool when you need to leverage serverless compute with GPU acceleration and headless browsing capabilities. It enables MCP-aware agents to drive modal compute, solving problems related to resource-intensive tasks and automated web browsing with screenshot generation. Ideal for use cases requiring efficient, scalable compute and automated web interaction, with inputs including compute tasks and outputs including screenshots and computation results.

Canonical page: https://skillsregistry.net/skills/salus-ryan-pi-modal-mcp  
JSON: https://api.skillsregistry.net/v1/skills/salus-ryan-pi-modal-mcp

## Description

Enables MCP-aware agents to drive Modal serverless compute, including GPU workers and headless Chromium for web browsing with screenshots.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ancf83cvs8)
- **Repository:** <https://github.com/salus-ryan/pi-modal-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "salus-ryan-pi-modal-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/salus-ryan-pi-modal-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/salus-ryan-pi-modal-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt