MCP is emerging as shared infrastructure across the production-agentic literature: Eranga et al. 2025 prescribe tool-first design over MCP with clean separation between workflow logic and MCP servers, while Yue et al. 2026's perspective on MCP-native AI scientist ecosystems cites MCP construction tooling such as Code2MCP alongside work on measuring agents in production.
E5 supports the Eranga practices and E7's reference list does contain 'Code2mcp: transforming code repositories into mcp services' and 'Measuring agents in production,' but the cited Yue chunk is only a bibliography and does not establish that Yue et al. 2026 is 'a perspective on MCP-native AI scientist ecosystems.'
Written by Kimi K3 via Ollama Cloud · checked by GLM-5.3 via Ollama Cloud · 1 Oct, 04:35
Source chain
AEvery quote below was checked, without a model, to appear verbatim in its source.
- 01
“tool-first design over MCP”
Full-text passage · p. 2 · evidence E5
ing, developing, and deploying production-quality agentic AI systems. We introduce a structured engineering lifecycle encompassing workflow decomposition, multi-agent design patterns, Model Context Protocol(MCP), and tool integration, deterministic orchestration, Responsible-AI considerations, and environment-aware deployment strategies. We then present nine core best practices for engineering production-grade agentic AI workflows, including tool-first design over MCP, pure-function invocation, single-tool and single-responsibility agents, externalized prompt management, ResponsibleAI-aligned model-consortium design, clean separation between workflow logic and MCP servers, containerized deployment for scalable operations, and adherence to the Keep it Simple, Stupid (KISS) principle to maintain simplicity and robustness. To demonstrate these principles in practice, we present a comprehensive case study: a multimodal news-analysis and media-generation workflow. By combining architectural guidance, operational patterns, and practical implementation insights, this paper offers a foundational reference to build robust, extensible, and production-ready agentic AI workflows.
Passage read from arxiv.org, which may be a preprint rather than the published version.
- 02
“Code2mcp: transforming code repositories into mcp services”
Full-text passage · no page number · evidence E7
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.
- 03
“Measuring agents in production”
Full-text passage · no page number · evidence E7
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.