KYVAutoResearch2MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
KYVAutoResearch v2
项目制的自动研究 Agent 框架。让 AI 围绕研究主题把证据穷尽到可以下判断的程度;证据不足时,如实说出来。 Project-based Auto-Research AI Agent Framework. Exhausts evidence until a judgment can be made; honestly states "insufficient evidence" when there isn't enough.
English | 中文
📖 目录 | Table of Contents
项目简介 | Introduction
KYVAutoResearch 是一个项目制的自动研究 Agent 框架。它不同于普通的对话式 AI,而是围绕研究主题建立问题树,用问题 × 证据矩阵追踪证据,按证据等级判定。它的核心承诺是:证据不足时,如实输出“无法判断”,绝不编造。
KYVAutoResearch is a project-based auto-research AI agent framework. Unlike standard conversational AI, it builds a problem tree around a research topic, tracks evidence using a Problem × Evidence Matrix, and makes judgments based on evidence levels. Its core promise: when evidence is insufficient, it honestly outputs "Unable to determine" instead of hallucinating.
核心概念 | Core Concepts
问题 × 证据矩阵 | Problem × Evidence Matrix:追踪每一条证据与问题的对应关系,确保没有无证据的结论。
双通道判定 | Dual-channel Judgment:确保证据充分且逻辑自洽。
证据分级与缺口识别 | Evidence Grading & Gap Identification:自动识别证据不足的环节,拒绝在覆盖率未满 100% 时给出“已解决”的建议。
MCP Server + Dual Skill:包含
KYVAutoResearch2MCP,支持与 Claude Desktop 等客户端无缝集成,并配有双 Skill 设计。
快速开始 | Quick Start
(如果你已经发布到 PyPI,请把下方替换为 pip install 你的包名)
If not published to PyPI, install from source:
git clone https://github.com/kyvjyf/KYVAutoResearch-v2.git
cd KYVAutoResearch-v2👉 查看完整使用说明 | See Full Documentation
项目结构 | Project Structure
KYVAutoResearch-v2/
├── core/ # 核心逻辑与引擎
├── schema_migrations/ # 数据库模式迁移
├── scripts/ # 辅助脚本
├── skills/ # 双 Skill 设计
├── tools/ # 工具集
├── server.py # MCP Server 入口
├── pyproject.toml # 项目依赖配置
└── 使用说明.md # 完整使用文档设计文档 | Design Documentation
关于系统的详细设计理念和架构说明,请参阅:
边界说明 | Notes
本分享版不包含测试套件、演示脚本与研究数据。 This shared version does not include the test suite, demo scripts, or research data.
反馈 | Feedback
欢迎在 Issues 中反馈问题或建议: Feel free to provide feedback or suggestions in Issues: https://github.com/kyvjyf/KYVAutoResearch-v2/issues
License: MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared research, saved evidence, independent reviews and open tasks for AI agents.
Source-traced evidence research for AI agents. We organise the evidence; you decide.
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
Open evidence base built by AI agents: server-checked quotes, blind review, Erdős literature checks.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMakes AI research agents accountable by giving every conclusion a traceable argument graph. Provides a persistent argument graph where claims require grounds and warrants for auditable, verifiable reasoning.3MIT
- AlicenseBqualityCmaintenanceEnables AI agents to conduct local, auditable opportunity discovery by collecting public discussions, tracing claims to exact quotes and source provenance, testing claims with counterevidence, and exporting deterministic evidence packs.471MIT
- AlicenseAqualityCmaintenanceEnables agents to search and reference trusted, out-of-band ingested source state, run claim-bound document reviews, validate evidence-status proposals against admissibility guards, and build evidence matrices. It keeps proposal, evidence, admissibility, and adjudication separate so agents can propose epistemic statuses without creating the source facts, page locators, provenance, or missingness records that support them.5MIT
- AlicenseCqualityBmaintenanceGives any MCP client 27 tools for turning scattered feeds, forums, and media into a persistent, searchable evidence corpus, so an agent can search and import evidence, verify claims with independent-source counting and citation checks, and run multi-round research that produces cited, revisable reports. It also supports adaptive retrieval widening, tiered evidence where only author-written sections count as sources, and honest degradation when no LLM key is available.27MIT