ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

openviking-mcp

Set up and run the OpenViking MCP server for RAG capabilities. Use when users need semantic search and document Q&A exposed through Model Context Protocol for Claude Desktop/CLI or other MCP clients. Triggers on requests about OpenViking MCP, RAG servers, or semantic search MCP setup.

Why use this skill?

Easily index and search your local documents and web resources using the OpenViking MCP server. Enable context-aware Q&A with your own data.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/zaynjarvis/openviking-mcp
Or

What This Skill Does

The openviking-mcp skill allows you to integrate the OpenViking RAG (Retrieval-Augmented Generation) server directly into your AI workflow via the Model Context Protocol (MCP). This enables your AI agent to query, index, and search local files, directories, and web URLs using semantic search. By acting as an intermediary between your documents and the LLM, it provides context-aware answers based on your private knowledge base. It is designed to bridge the gap between static documents and dynamic LLM reasoning.

Installation

To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/zaynjarvis/openviking-mcp.

Once installed, ensure you have Python 3.13+ and uv installed. Navigate to the openviking/examples/mcp-query directory, run uv sync, and configure your ov.conf file with your OpenAI API keys for LLM and embedding services. You can start the server using uv run server.py. Finally, connect the server to Claude Desktop by adding the configuration entry to your ~/.mcp.json file pointing to http://localhost:8000/mcp. Always ensure your API keys are protected and not hard-coded in version control.

Use Cases

  • Personal Knowledge Management: Use this to query large collections of PDF reports or markdown notes without manually searching through files.
  • Technical Documentation Search: Index complex codebases or internal documentation to get instant summaries or architectural insights.
  • Web Research Aggregation: Use the add_resource tool to ingest URLs of articles or research papers and query the collective findings to draft syntheses.

Example Prompts

  1. "Index the folder ~/projects/marketing-docs and tell me what the Q4 strategy documents say about growth."
  2. "Find any documents in my database that mention internal API security protocols and explain them to me."
  3. "Search my knowledge base for 'customer feedback' and provide a summary of the most common complaints."

Tips & Limitations

  • Security: Because this skill connects to an external API (OpenAI), ensure you are comfortable with your indexed data embedding processing.
  • Configuration: Always keep ov.conf in your local directory for easy access, but do not share it.
  • Performance: Large documents may take time to index; check your terminal for logs if the indexing seems stalled.
  • Model Selection: You can swap models in the config, but ensure your vlm model supports the complexity of your queries.
Read Full Documentation on GitHub

Metadata

Author@zaynjarvis
Stars879
Views12
Updated2026-02-11
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-zaynjarvis-openviking-mcp": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#rag#mcp#semantic-search#knowledge-base#documentation
Safety Score: 3/5

Flags: file-read, file-write, external-api

Related Skills

email-processor

Automate Gmail inbox processing - categorizes unread emails, marks marketing/newsletters/promotions as read, and surfaces important emails requiring attention. USE WHEN: User asks to "check my emails", "process unread emails", "clean up my inbox", "mark newsletters as read", or any Gmail automation task. REQUIRES: gog CLI (brew install steipete/tap/gogcli) + Google Cloud OAuth credentials

zaynjarvis 879

openviking

RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource".

zaynjarvis 879