What is the key difference between Knowledge Rag and Deja Vu?

Knowledge Rag belongs to the Knowledge & Memory category with local stdio execution, while Deja Vu belongs to the Knowledge & Memory category with local stdio execution.

How do I install Knowledge Rag or Deja Vu in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Knowledge Rag and Deja Vu free or paid?

Knowledge Rag operates under a Free / Open Source model (No auth required). Deja Vu operates under a Free / Open Source model (No auth required).

Which MCP server has more tools and community activity?

Knowledge Rag lists 6 tools with 3 views and 243 GitHub stars. Deja Vu lists 6 tools with 1 views and 609 GitHub stars.

Can I use both Knowledge Rag and Deja Vu together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

How do I install Knowledge Rag or Deja Vu in Claude Desktop, Cursor, or Windsurf?

Both servers follow the standard Model Context Protocol configuration format. Simply copy the JSON block from the configuration section above and paste it into your AI client's mcpServers configuration object (for instance in claude_desktop_config.json or ~/.cursor/mcp.json ), then completely restart or refresh the application.

Are Knowledge Rag and Deja Vu free to use, or do they require API keys?

Knowledge Rag is listed under a Free / Open Source model with No auth required . Deja Vu operates under a Free / Open Source model with No auth required . If environment variables are required (such as API keys), be sure to define them under the env key in your MCP client's configuration file.

Can I run both Knowledge Rag and Deja Vu at the same time in my AI client?

Yes! MCP clients support multi-server orchestration. You can include both lyonzin-knowledge-rag and vshulcz-deja-vu as distinct keys inside the single mcpServers object in your configuration file. Your AI assistant will automatically select and call the appropriate tool from either server during chat sessions.

Which MCP server has higher directory engagement and quality ratings?

On AllMCPs, Knowledge Rag has a Quality Score of 48 /100 ( Fair ) with 3 views, 0 installs, and 243 GitHub stars. Deja Vu holds a Quality Score of 53 /100 ( Good ) with 1 views, 0 installs, and 609 GitHub stars.

Side-by-Side Model Context Protocol Comparison

Knowledge Rag vs Deja Vu

In-depth architectural comparison of the Knowledge Rag and Deja Vu MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

Knowledge Rag

Knowledge & Memory · Local stdio

Quality: 48/100 (Fair) | Auth: No auth required

Deja Vu

Knowledge & Memory · Local stdio

Quality: 53/100 (Good) | Auth: No auth required

Verdict Summary: Choose Knowledge Rag if you need specialized Knowledge & Memory tools running via a local process. Choose Deja Vu if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose Knowledge Rag when:

You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Hybrid search combining BM25, semantic vectors, and cross-encoder reranking, Supports 20+ file formats including markdown, PDFs, code, notebooks, 13 MCP tools exposing search and retrieval capabilities.

Explore Knowledge Rag Details

Choose Deja Vu when:

You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Zero-dependency single binary, fully local operation, Search 3.5 GB of session history in ~1.5 ms, Supports multiple coding agents via MCP protocol.

Feature & Specification Comparison

Specification	Knowledge Rag lyonzin Knowledge & Memory	Deja Vu vshulcz Knowledge & Memory
Summary	Local RAG system for Claude Code with hybrid search (BM25 + semantic), cross-encoder reranking, markdown-aware chunking, query expansion, and 28 MCP tools. Runs entirely offline with zero external servers.	Local memory layer over the session histories coding agents already write (Claude Code, Codex CLI, opencode): lexical search, recall tools, session-start auto-recall, secret redaction at index time, cross-machine sync over SSH.
Category & Scope	Knowledge & Memory

Tools & Capabilities Breakdown

Knowledge Rag Tools (6)

Hybrid search combining BM25, semantic vectors, and cross-encoder reranking

Supports 20+ file formats including markdown, PDFs, code, notebooks

13 MCP tools exposing search and retrieval capabilities

Markdown-aware chunking and query expansion

Runs entirely offline via ONNX with optional NVIDIA GPU acceleration

Supports SSE and streamable HTTP transports for concurrent access

Deja Vu Tools (6)

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

Knowledge Rag Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "lyonzin-knowledge-rag": {
      "command": "npx",
      "args": [
        "-y",
        "lyonzin-knowledge-rag"
      ]
    }
  }
}

Deja Vu Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "vshulcz-deja-vu": {
      "command": "npx",
      "args": [
        "-y",
        "@vshulcz/deja-vu"
      ]
    }
  }
}

Frequently Asked Questions

Knowledge Rag is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Deja Vu belongs to Knowledge & Memory using local stdio subprocess. Select Knowledge Rag when you need capabilities focused on knowledge & memory and Deja Vu when you require tools for knowledge & memory.

More alternatives to Knowledge Rag More alternatives to Deja Vu Knowledge & Memory category hub