ceph-doc-kb
Enables semantic and keyword search of Ceph documentation with version-aware, component-scoped indices, supporting command lookup and code example retrieval.
README
ceph-doc-kb
Version-aware, component-scoped Ceph documentation knowledge base. Indexes Ceph RST docs into per-component vector indices with two-tier search (BM25 + semantic via fastembed/FAISS).
Quick Start
# Install
pip install -e .
# Build index from Ceph docs
git clone --depth 1 --branch v20.2.1 --sparse https://github.com/ceph/ceph.git /tmp/ceph-docs
cd /tmp/ceph-docs && git sparse-checkout set doc
cd /path/to/ceph-doc-kb
python3 index_docs.py --docs-path /tmp/ceph-docs/doc --version 20.2.1 --verbose
Architecture
- Component-scoped indices: Each Ceph component (rados, rbd, rgw, cephfs, cephadm) gets its own FAISS index for fast, targeted search
- Two-tier search: BM25 keyword match for exact terms, fastembed semantic search for conceptual queries
- Command cross-reference: Instant lookup from any
ceph/rbd/radoscommand to relevant docs - Quality scoring: Chunks with code examples, commands, and explanations rank higher
- Version-aware: Supports multiple Ceph release indices side by side
MCP Server
{
"mcpServers": {
"ceph-doc-kb": {
"command": "python3",
"args": ["-m", "ceph_doc_kb.server.mcp_server"],
"cwd": "/path/to/ceph-doc-kb"
}
}
}
Tools
| Tool | Description |
|---|---|
search_docs |
Search docs with optional component scoping |
search_examples |
Search code examples and configs |
get_doc_page |
Get full doc page content |
find_docs_for_command |
Instant command-to-doc lookup |
list_components |
List available components |
list_topics |
List topics within a component |
capabilities |
Server capabilities |
health |
Index health status |
REST API
python3 -m ceph_doc_kb.server.rest_api
# http://127.0.0.1:8100/api/search?query=erasure+coding&component=rados
See BOB_INTEGRATION_GUIDE.md for full endpoint reference with curl examples.
VS Code Extension
A VS Code extension is available for interactive documentation search:
cd vscode-extension && npm install
# Install via "Developer: Install Extension from Location..."
Features: search docs (Cmd+Alt+D), search examples (Cmd+Alt+E), find docs for command (Cmd+Alt+F), insert code at cursor.
See vscode-extension/README.md for details.
Agent Integration
Python client for LLM agents (no external dependencies):
from examples.agent_integration import CephDocKBClient
client = CephDocKBClient("http://localhost:8100")
results = client.search_docs("erasure coding", component="rados")
LangChain and CrewAI wrappers included. See BOB_INTEGRATION_GUIDE.md.
Incremental Updates
python3 index_docs.py --update --docs-path /tmp/ceph-docs/doc \
--repo-path /tmp/ceph-docs --from-version v20.2.1 --to-version v20.2.2
Documentation
| Document | Description |
|---|---|
| SPEC.md | MCP platform contract and entity schema |
| DEVELOPMENT.md | Architecture, source tree, maintainer guide |
| BOB_INTEGRATION_GUIDE.md | REST API reference, agent integration, deployment |
| vscode-extension/README.md | VS Code extension install and usage |
Development
pip install -e ".[dev]"
pytest
See DEVELOPMENT.md for architecture details and contributing.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。