# MCP Science

> Use this tool when you need to streamline access to multiple scientific research servers and tools, solving problems of manual installation and dependency management for researchers and AI developers. It provides a unified command-line interface for discovering, installing, and running scientific MCP servers from local or remote sources, with automatic dependency handling. Ideal for use cases requiring easy deployment and testing of specialized scientific tools across various research domains.

Canonical page: https://skillsregistry.net/skills/pathintegral-institute-science  
JSON: https://api.skillsregistry.net/v1/skills/pathintegral-institute-science

## Description

This MCP server launcher provides a unified command-line interface for discovering and running scientific research MCP servers from the Path Integral Institute's collection. Built with Python and Click, it uses uvx to dynamically install and execute servers from either local development directories or remote Git branches, automatically handling dependencies and offering branch-specific deployment for testing new features. The implementation serves as a package manager and launcher for scientific computing MCP servers, making it valuable for researchers who need easy access to multiple specialized scientific tools without manual installation of each server, and for developers building AI assistants that require programmatic access to scientific computing capabilities across different research domains.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pathintegral-institute-science)
- **Repository:** <https://github.com/pathintegral-institute/mcp.science>

## 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": "pathintegral-institute-science"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pathintegral-institute-science` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pathintegral-institute-science/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