Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

# Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System
Source: [https://arxiv.org/abs/2606.04494](https://arxiv.org/abs/2606.04494)
[View PDF](https://arxiv.org/pdf/2606.04494)

> Abstract:Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highly heterogeneous in interfaces and execution environments, while agent planning still relies on flat prompt\-retrieved tool descriptions\. As biomedical software ecosystems grow, this coupling between tool coverage and context size leads to tool confusion, unstable planning, and inefficient execution\. We introduce BioManus, an MCP\-native biomedical agent built on graph\-scaffolded planning over structured biological capabilities\. BioManus first introduces the BioinfoMCP Compiler, which converts heterogeneous bioinformatics software into standardized MCP servers, yielding a large executable MCP ecosystem\. It then organizes this ecosystem as a typed heterogeneous MCP graph over tools, operations, datatypes, and workflow stages\. At inference time, BioManus retrieves compact task\-specific subgraphs, synthesizes operation\-level workflow scaffolds\. This design decouples planning complexity from raw tool inventory size, achieving a context compression ratio of Theta\(N / \(h \* m\_bar\)\) under high\-recall retrieval, where N is the total tool count, h is the workflow horizon, and m\_bar \(much smaller than N\) is the average number of candidate tools per operation\. Experiments on BioAgentBench and LAB\-Bench show that BioManus improves execution accuracy, workflow validity, and context efficiency over advanced biomedical agent baselines\. This work suggests a paradigm shift: scalable biomedical reasoning requires structured executable capability graphs rather than increasingly larger prompt\-level tool retrieval\.

## Submission history

From: Zhangtianyi Chen \[[view email](https://arxiv.org/show-email/4ef2fc34/2606.04494)\] **\[v1\]**Wed, 3 Jun 2026 06:19:25 UTC \(987 KB\)