# PRIMS (Python Runtime)

> Use this tool when you need to execute Python code securely in a sandbox environment with persistent workspaces and configurable dependencies. It solves problems in data science workflows, AI computational tasks, and multi-step analytical processes by providing isolated code execution, remote file mounting, and output artifact capture. It takes in Python code and dependencies as input and outputs artifacts like plots and CSV files via HTTP endpoints or presigned URLs.

Canonical page: https://skillsregistry.net/skills/prims  
JSON: https://api.skillsregistry.net/v1/skills/prims

## Description

PRIMS (Python Runtime Interpreter MCP Server) provides AI assistants with secure Python code execution capabilities through an isolated sandbox environment built with FastMCP and Docker. The implementation creates session-persistent workspaces where code runs in virtual environments with configurable pip requirements, supports mounting remote files for data analysis workflows, and automatically captures output artifacts like plots and CSV files that can be served via HTTP endpoints or uploaded to presigned URLs. Built by Hileamlak Mulugeta Yitayew with comprehensive tooling including workspace inspection, file mounting, and artifact persistence, PRIMS serves developers needing reliable Python execution for data science workflows, AI assistants requiring computational capabilities with file I/O, and applications where secure code sandboxing with session persistence is essential for multi-step analytical tasks.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/prims)
- **Repository:** <https://github.com/hileamlakb/python-runtime-interpreter-mcp-server>

## 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": "prims"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/prims` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/prims/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