by tririver · MCP Server · ★ 40
ARC Agent Research Copilot (ARC) is a cache-first research toolkit for theoretical-physics papers and paper-centered research workflows. It gives an agent, or a human using the command line, structured access to arXiv full text, INSPIRE metadata, references, citers, paper summaries, research-domain graphs, and multi-agent idea/calculation workflows. ARC is built around five Python command line tools; also runs the optional MCP server: : paper metadata, references, citers, ar5iv sections, equation context, full-text search, LLM paper summaries, and paper-summary batches.
| Stars | 40 |
| Forks | 7 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.7476322002829/100 |
| Last Updated | 2026-07-07 |
| Created | 2026-05-23 |
| Platforms | mcp, python |
| Est. Tokens | ~19k |
These tools work well together with arc for enhanced workflows:
Explore other popular mcp server tools:
arc is Agent Research Copilot (ARC) is a set of skills and tools (MCP) for theoretical physics literature review, idea generation and performing calculations.. It is categorized as a MCP Server with 40 GitHub stars.
arc is primarily written in Python.
You can find installation instructions and usage details in the arc GitHub repository at github.com/tririver/arc. The project has 40 stars and 7 forks, indicating an active community.
arc is released under the MIT license, making it free to use and modify according to the license terms.