# Knowledge Raven

Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad sear…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add knowledge-raven/RAV3N

# Browse available tools
npx -y @smithery/cli@latest tool list knowledge-raven/RAV3N

# Get full schema for a tool
npx -y @smithery/cli@latest tool get knowledge-raven/RAV3N list_knowledge_bases

# Call a tool
npx -y @smithery/cli@latest tool call knowledge-raven/RAV3N list_knowledge_bases '{}'
```

## Direct MCP Connection

Endpoint: `https://rav3n--knowledge-raven.run.tools`

## Tools (6)

- `list_knowledge_bases` — Lists all available knowledge bases with document counts.
- `search_knowledge_base` — Targeted search for specific facts, definitions, or narrow questions. Returns up to 10 best matches with context. Each …
- `broad_search` — Keyword-heavy search for overview, comparison, and exploratory questions ('What tools do we use?', 'List all...'). Retu…
- `list_documents` — Lists all documents in a knowledge base with titles, types, AI-generated summaries, and source_link for each document. …
- `fetch_document` — Retrieves document content flexibly. Modes: 'preview' (first 3 sections + summary), 'full' (entire document), 'chunks' …
- `get_document_metadata` — Retrieves metadata for a document (title, type, size, page count, etc.) including a source_link to view the document on…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get knowledge-raven/RAV3N <tool-name>
```