SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents

TL;DR

SCP introduces a standardized protocol and architecture to enable a global network of autonomous scientific agents, streamlining resource discovery, experiment management, and collaboration across institutions to accelerate scientific discovery.

Contribution

The paper presents SCP, a novel open-source standard and system architecture for unified resource integration and experiment lifecycle management in autonomous scientific research.

Findings

Over 1,600 tool resources integrated into SCP platform

Facilitates secure, large-scale collaboration among AI systems and researchers

Reduces integration overhead and improves reproducibility in scientific workflows

Abstract

We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science.