# Multi-Agent Research Sandbox

> Use this tool when you need to integrate reliable web research, document parsing, and PDF analysis capabilities into your AI agents. It solves problems related to information gathering, academic paper analysis, and content processing through its modular architecture and interfaces with MCP protocol and REST API. Ideal for developers building AI agents requiring flexible deployment options and configurable LLM backends for web search, content parsing, and paper processing.

Canonical page: https://skillsregistry.net/skills/sjtu-sai-agents-research-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/sjtu-sai-agents-research-sandbox

## Description

This MCP sandbox implementation by SJTU SAI Agents provides a multi-layered architecture for web search, document parsing, and PDF analysis through both MCP protocol and REST API interfaces. Built with Python and FastAPI, it integrates Google search capabilities, web content parsing with LLM analysis, and ArXiv paper processing using models like GPT-4 and Qwen. The implementation features a modular design with separate API proxy services, configurable LLM backends, and comprehensive tool management through both MCP clients and direct HTTP calls. It serves developers building AI agents that need reliable web research capabilities, academic paper analysis, and flexible deployment options across different integration patterns.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sjtu-sai-agents-research-sandbox)
- **Repository:** <https://github.com/sjtu-sai-agents/mcp_sandbox>

## 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": "sjtu-sai-agents-research-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sjtu-sai-agents-research-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sjtu-sai-agents-research-sandbox/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