OpenViking MCP Server
Integrates the OpenViking context database with Cloudwise SA Workflow Skills to enable semantic search and access to product catalogs or solution templates. It supports hierarchical context loading for optimized token usage and includes a mock mode for testing without a live backend.
README
OpenViking MCP Server
MCP Server for integrating OpenViking context database with Cloudwise SA Workflow Skills.
Features
- Semantic Search: Query knowledge base with natural language
- Product Catalog: Access Cloudwise product information (APM, DOEM, CMDB, etc.)
- Solution Templates: Retrieve industry-specific solutions
- Hierarchical Context: L0/L1/L2 tiered loading for optimal token usage
- Mock Mode: Test without real OpenViking server or API keys
Quick Start
Installation
cd openviking-mcp
pip install -e ".[dev]"
Mock Mode (No API Key Required)
# Run in mock mode for testing
export OPENVIKING_MOCK_MODE=true
python -m openviking_mcp.server
Real Mode (Requires OpenViking Server)
# Start OpenViking server first
openviking-server --port 1933
# Then run MCP server
export OPENVIKING_URL=http://localhost:1933
python -m openviking_mcp.server
Configuration
Environment variables:
| Variable | Default | Description |
|---|---|---|
OPENVIKING_URL |
http://localhost:1933 |
OpenViking HTTP API URL |
OPENVIKING_STORE |
cloudwise-kb |
Default store name |
OPENVIKING_TIER_DEFAULT |
L1 |
Default context tier (L0/L1/L2) |
OPENVIKING_MOCK_MODE |
false |
Enable mock mode for testing |
OPENVIKING_HTTP_TIMEOUT |
30 |
HTTP request timeout |
Claude Desktop Configuration
Add to ~/.claude/mcp-servers/openviking-mcp.json:
{
"name": "openviking-mcp",
"transport": "stdio",
"command": "python",
"args": ["-m", "openviking_mcp.server"],
"env": {
"OPENVIKING_URL": "http://localhost:1933",
"OPENVIKING_STORE": "cloudwise-kb",
"OPENVIKING_MOCK_MODE": "false"
}
}
Available Tools
| Tool | Description |
|---|---|
query_kb |
Semantic search across knowledge base |
get_product |
Get Cloudwise product details |
get_solution |
Retrieve solution templates |
list_directory |
Browse KB directory structure |
get_context_tier |
Get L0/L1/L2 context levels |
Development
# Run tests
pytest tests/ -v
# Run with coverage
pytest tests/ --cov=openviking_mcp
# Run mock mode demo
python scripts/demo_mock.py
# Lint
ruff check src/
mypy src/
Mock Mode
Mock mode provides simulated responses for development and testing without requiring:
- OpenViking server running
- Embedding API keys
- Actual knowledge base data
Enable mock mode:
export OPENVIKING_MOCK_MODE=true
Architecture
22 SA Skills → MCP Client → MCP Server → HTTP Client → OpenViking API → KB
↓
Mock Mode (可选)
License
MIT
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.