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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.