Make provenance and evidence traceability first-class for mcp openapi (openapi mcp server bridge stdio)

[haasonsaas]

Summary

Carry source, decision, and output provenance through the main workflow so downstream agents can audit and cite it.

This issue was generated from an org-wide EvalOps mining pass on 2026-05-10 07:57 UTC. It combines live GitHub repo signals with a per-repo arXiv search. Treat the research links as grounding for a concrete implementation, not as a request for a literature review.

Repo Evidence

• Repository description: OpenAPI 3.x to MCP server bridge in TypeScript with stdio, StreamableHTTP, and SSE transports
• Tree signals: 0 docs files, 2 workflows, 0 proto files, 14 test-like files.
• Anchor files sampled: README.md, package.json

Research Grounding

Repo axes: tooling, security, evaluation, governance

Search keywords: run, assert, const, npm, test, await, openapi, import, match, json, node, spec

• arXiv:2602.01129v1 SMCP: Secure Model Context Protocol (Xinyi Hou, Shenao Wang, Yifan Zhang, Ziluo Xue, Yanjie Zhao, Cai Fu), 2026.
• arXiv:2508.07575v1 MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark (Shiqing Fan, Xichen Ding, Liang Zhang, Linjian Mo), 2025.
• arXiv:2407.00121v1 Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks (Ibrahim Abdelaziz, Kinjal Basu, Mayank Agarwal, Sadhana Kumaravel, Matthew Stallone, Rameswar Panda), 2024.
• arXiv:2410.17950v1 Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling (Nirav Bhan, Shival Gupta, Sai Manaswini, Ritik Baba, Narun Yadav, Hillori Desai), 2024.
• arXiv:2602.18764v2 The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol (Andreas Schlapbach), 2026.
• arXiv:2507.19570v1 MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization (Yiting Wang, Wanghao Ye, Yexiao He, Yiran Chen, Gang Qu, Ang Li), 2025.
• arXiv:2601.22129v2 SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents (Yifeng Ding, Lingming Zhang), 2026.
• arXiv:2504.00914v1 On the Robustness of Agentic Function Calling (Ella Rabinovich, Ateret Anaby-Tavor), 2025.
• arXiv:2509.20415v2 Online-Optimized RAG for Tool Use and Function Calling (Yu Pan, Xiaocheng Li, Hanzhao Wang), 2025.
• arXiv:2510.25694v1 Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents (Jiayi Kuang, Yinghui Li, Xin Zhang, Yangning Li, Di Yin, Xing Sun), 2025.

What To Build

• Add stable identifiers for source records, derived decisions, and emitted outputs.
• Thread those identifiers through logs/events/API responses without leaking secrets.
• Provide a query or debug surface that reconstructs the chain for one completed workflow.

Acceptance Criteria

• A short design note names the repo-specific workflow, threat or correctness model, and the research assumptions being adopted.
• A runnable check, fixture, or verifier exercises the new contract in CI or an equivalent local command documented in the repo.
• The implementation emits or stores enough evidence for a downstream agent/operator to cite inputs, decisions, and outputs.
• At least one negative/degraded-mode case is covered so failures are observable rather than silently accepted.
• Documentation links the new behavior to the relevant EvalOps platform primitive or explicitly records why this repo remains standalone.

Notes

• Generated issue 2/5 for evalops/mcp-openapi by evalops_org_miner.py.
• Before implementation, confirm the sampled latent-spec snippets still match main; this issue intentionally cites exact file paths/lines where the mining pass saw them.