OpenViking MCP Server
Lightweight MCP server that connects to OpenViking for semantic search, resource management, and memory storage via natural language.
README
OpenViking MCP Server
A lightweight MCP (Model Context Protocol) server that connects to a running OpenViking server via HTTP, exposing its context database capabilities to Claude Desktop and other MCP clients.
No native compilation required -- only depends on httpx and mcp.
Prerequisites
- Python 3.10+
- A running OpenViking server (
openviking-serveron port 1933 by default)
Installation
pip install ./openviking-mcp
# or with uv
uv pip install ./openviking-mcp
Claude Desktop Setup
Add to your claude_desktop_config.json:
{
"mcpServers": {
"openviking": {
"command": "openviking-mcp",
"args": ["--server-url", "http://localhost:1933"],
"env": {
"OPENVIKING_API_KEY": "your-key-here"
}
}
}
}
Claude Code Setup
claude mcp add openviking -- openviking-mcp --server-url http://localhost:1933
Or with HTTP transport:
openviking-mcp --transport streamable-http --port 2033
claude mcp add --transport http openviking http://127.0.0.1:2033/mcp
Available Tools
| Tool | Description |
|---|---|
search |
Semantic search across memories, documents, and resources |
add_resource |
Ingest a file, directory, or URL for indexing |
read_content |
Read the full content of a resource by URI |
get_overview |
Get a structured summary of a resource (L1) |
get_abstract |
Get a one-line summary of a resource (L0) |
list_contents |
Browse directory contents at a Viking URI |
add_memory |
Store information for future recall |
find_by_pattern |
Find resources by filename glob pattern |
grep_content |
Exact text/regex search within resources |
get_resource_info |
Get resource metadata (type, size, status) |
get_relations |
View links between resources |
health_check |
Check OpenViking server connectivity |
CLI Options
| Flag | Env Var | Default | Description |
|---|---|---|---|
--server-url |
OPENVIKING_URL |
http://localhost:1933 |
OpenViking server URL |
--api-key |
OPENVIKING_API_KEY |
API key for authentication | |
--transport |
stdio |
stdio or streamable-http |
|
--host |
127.0.0.1 |
Bind host (HTTP transport) | |
--port |
OPENVIKING_MCP_PORT |
2033 |
Bind port (HTTP transport) |
--timeout |
60 |
HTTP request timeout (seconds) | |
--debug |
OPENVIKING_MCP_DEBUG |
false |
Enable debug logging |
License
Apache-2.0
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.