Connecting AI Agents to Scientific Tools with MCP: My OSI Hackathon 2026 Experience

说明与用途

在OSI Hackathon 2026期间，团队构建了一个MCP服务器，使AI代理能够访问科学工具，并使用它对26S蛋白酶体缺失数据进行补全，合作伙伴基础覆盖率达到95.1%。

问题

Single‑cell proteomics experiments often miss 20–60% of protein measurements, requiring imputation. Traditional k‑NN methods rely only on existing data patterns, so the team explored whether biological knowledge, especially protein‑complex relationships, could improve imputation accuracy.

结果

The MCP integration allowed AI agents to access and invoke specialized scientific tools, enabling a real‑world imputation experiment that achieved 95.1% partner‑based coverage for missing 26S proteasome subunits.

工作流

• Clone KnowledgeIsPower repo and activate Python virtual environment
• Run offline tests (19 passed, 27 xfailed) to verify MCP server tools
• Configure Claude Code CLI as an MCP client using STDIO transport
• Configure GitHub Copilot CLI as an MCP client using STDIO transport
• Use Copilot CLI to query get_complexes for PSMB5 and retrieve 26S proteasome subunits
• Prepare a 26S‑only .h5ad subset from Petrosius 2023 dataset
• Invoke impute_with_prior with Complex Portal prior to impute missing values
• Collect and interpret imputation metrics (total missing, partner‑based, kNN fallback, coverage)

证据

Our team explored whether biological knowledge, particularly relationships between proteins, could improve these estimates.

来源

We developed scp-graphfs-mcp, a scientific Model Context Protocol (MCP) server that enables AI agents to interact with protein-complex data, knowledge graphs, and imputation tools.

来源

The resulting metrics were: Total missing values 638, Imputed from protein partners 607, kNN fallback imputations 31, Partner-based coverage 95.1%

来源

I successfully configured the connection and verified that Claude Code recognized the MCP server.

来源