knowledgehub
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@knowledgehub search daily-work for API design patterns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
KnowledgeHub
KnowledgeHub 是面向本地多知识库的统一扫描、增量索引和 AI 检索基础设施。
它不搬运原始文件,而是注册多个知识目录,检测新增、修改和删除,更新本地 SQLite/FTS5 全文索引,并通过只读 MCP 同时向 Claude Code 和 Codex 提供带绝对路径、章节、行号和原文片段的检索能力。
当前状态
实现版本:
0.1.0运行时:Python
3.12项目目录:
/Users/your-user/KnowledgeHub实际配置:
config/knowledge-bases.yaml索引数据库:
index/knowledge.db已启用知识库:
daily-work、business-dev首次真实索引:2026-07-16,共 850 个文档、16,610 个 chunks
AI 接入:Claude Code 与 Codex 均已注册用户级/全局
knowledgehubMCP调度:macOS launchd 每天本地时间 12:00 执行
kb reconcile --all通知:复用本机 Lark 机器人脚本发送任务摘要
Related MCP server: directory-indexer
已实现能力
多知识库、多根目录和
project_id路由Markdown、Text、YAML、JSON、HTML、PDF、DOCX 解析
SHA-256 增量检测与 Manifest 全量对账
SQLite WAL + FTS5 trigram 全文检索
1–2 字中文查询 LIKE 回退
显式
chunk_id关联、scope/project 过滤解析失败保留最后一次成功索引
敏感路径和敏感内容拒绝索引
只读 MCP:
kb_search、kb_read、kb_project_context、kb_statusPID 锁、stale lock 恢复、当天成功去重、Lark 重试与 outbox
快速使用
cd /Users/your-user/KnowledgeHub
# 校验配置
.venv/bin/kb config validate --config config/knowledge-bases.yaml
# 快速增量扫描:不做全局删除对账
.venv/bin/kb scan --scope daily-work --config config/knowledge-bases.yaml
# 完整 Manifest 对账:每日任务使用此命令
.venv/bin/kb reconcile --all --config config/knowledge-bases.yaml
# 全文检索
.venv/bin/kb search "半双工消息流" --scope daily-work --config config/knowledge-bases.yaml
# 项目知识路由
.venv/bin/kb project-context /Users/your-user/workspace/bit-news \
--config config/knowledge-bases.yaml
# 查看健康状态
.venv/bin/kb status --json --config config/knowledge-bases.yaml文档导航
文档 | 说明 |
总体架构、数据模型、检测、索引、调度、安全与测试 | |
已安装 MCP、项目指令、检索流程与验证 | |
已安装 MCP、AGENTS.md 规则与验证 | |
手动扫描、launchd、日志、Lark、备份与恢复 | |
真实索引、MCP、Lark、launchd 和测试验收结果 | |
多知识库、包含/排除规则、调度和通知配置 |
项目结构
/Users/your-user/KnowledgeHub/
├── AGENTS.md
├── CLAUDE.md
├── README.md
├── pyproject.toml
├── src/knowledgehub/
├── tests/
├── config/
│ ├── knowledge-bases.example.yaml
│ └── knowledge-bases.yaml # 本机实际配置,不提交凭据
├── docs/
├── deploy/
├── scripts/
├── index/ # SQLite 索引
├── run/ # PID、锁和当天成功标记
└── logs/ # 扫描日志、JSON 报告和通知 outbox安全边界
Indexer 不修改、不删除、不移动原始知识文件。
MCP 只提供读取和检索,不提供写入/删除工具。
.env、私钥、证书、Token、凭据文件默认拒绝索引。Lark Webhook 或应用凭据保留在项目目录外,不复制进 KnowledgeHub。
Available Tools
4 toolskb_project_contextB
Resolve an absolute project path to its indexed project documentation.
Inputs: project_path (required), limit. Returns: object
kb_readB
Read one indexed document or a specific indexed chunk.
Inputs: document_id (required), chunk_id. Returns: object
kb_searchB
Search indexed knowledge and return traceable document/chunk references.
Inputs: query (required), limit, scopes, project_id. Returns: object
kb_statusA
Return KnowledgeHub index health and last scan information.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct action: search, read, resolve project context, and check status. There is no functional overlap between them, so an agent can confidently select the right tool.
All tools share the consistent 'kb_' prefix and use snake_case, but two are verb-based (kb_search, kb_read) while two are noun-based (kb_project_context, kb_status). This is a minor deviation from a uniform verb_noun pattern.
With 4 tools, the server is well-scoped for querying a knowledge base. It is not too thin or overloaded, and each tool serves a clear purpose.
The tool set covers the core knowledge access workflows: search, read, get project context, and health status. Missing operations like listing all projects or documents are minor gaps that agents can work around via search.
Maintenance
Related MCP Connectors
Securely search and manage workspace context files for AI agents and teams.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Read and search folders on your own computer with explicit consent. Files are never uploaded.
Search your knowledge bases from any AI assistant using hybrid RAG.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read, search, and analyze local file systems with tools for reading file contents, listing directories, searching by patterns, and analyzing folder structures for context-aware queries.MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI assistants with semantic search and read access to local files and directories, enabling knowledge retrieval from indexed content.12 npm17MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.2MIT
- AlicenseAqualityFmaintenanceProvides LLMs with secure, read-only access to local documentation by scanning directories, extracting content from PDF, DOCX, Markdown, and text files, and performing keyword searches.34 npmMIT