How do I install the knowledge rag mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

It reads `KNOWLEDGE_RAG_SINGLE_INSTANCE` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

Knowledge Rag MCP Server

Drop your PDFs, markdown, code, notebooks — **1800+ files, 39K chunks, indexed in under 3 minutes.**

Local serverstdioPython

What is the Knowledge Rag MCP Server?

Drop your PDFs, markdown, code, notebooks — 1800+ files, 39K chunks, indexed in under 3 minutes.

Configuration and credentials

Python 3.11+ - Claude Code CLI - …or any other MCP client (Claude Desktop, Cursor, VS Code, Antigravity, opencode, Windsurf) — see Use with other MCP clients - ~200MB disk for model cache (auto-downloaded on first run) - Optional: NVIDIA GPU + CUDA 12 for accelerated embeddings (see GPU Acceleration below)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
v4.0.0	Enterprise concurrent access: SSE/HTTP transport (1 server → N clients), thread-safe shared state, optional rate limiting + Prometheus metrics, ChromaDB WAL mode, --transport CLI
v3.9.0	Quality Gate activated: 35+ automated PR checks across 7 pillars (Security, Stability, Memory Leak, Versatility, Scalability, Versioning, Quality) + nightly resilience suite (chaos, soak, determinism, mutation)
v3.8.1	Critical hotfix: loud-fail embeddings (no more silent zero-vector corruption); Windows CI flake erradicated (HF_HUB_OFFLINE + shell:bash + atexit wrapper)
v3.8.0	Lazy-load embeddings, opt-in single-instance guard, version sync across PyPI/NPM/Docker
v3.6.0	Multi-language code parsing (C/C++/JS/TS/XML), NPM wrapper, Docker image, automated release pipeline
v3.5.2	CUDA DLL auto-discovery from pip packages, graceful GPU→CPU fallback, explicit CPU provider (no CUDA noise when gpu: false), BASE_DIR resolution fix for editable installs
v3.5.1	Remove Python <3.13 upper bound — 3.13 and 3.14 now supported
v3.5.0	Optional GPU acceleration, supported formats table, full README rewrite
v3.4.3	MCP stdout save/restore fix (v3.4.2 broke JSON-RPC responses)
v3.4.0	Persistent model cache, exclude patterns, Jupyter Notebook parser, inotify resilience, MetaTrader support

How to install the Knowledge Rag MCP Server

{
  "mcpServers": {
    "knowledge-rag": {
      "command": "npx",
      "args": ["-y", "knowledge-rag"],
      "env": {
        "KNOWLEDGE_RAG_SINGLE_INSTANCE": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

Python 3.11+ - Claude Code CLI - …or any other MCP client (Claude Desktop, Cursor, VS Code, Antigravity, opencode, Windsurf) — see Use with other MCP clients - ~200MB disk for model cache (auto-downloaded on first run) - Optional: NVIDIA GPU + CUDA 12 for accelerated embeddings (see GPU Acceleration below)

Variable	Description	Required
KNOWLEDGE_RAG_SINGLE_INSTANCE	Configuration value read at startup.	Optional

Example prompts to try

“Use Knowledge Rag to v4.0.0.”
“Use Knowledge Rag to v3.9.0.”
“Use Knowledge Rag to v3.8.1.”

Frequently asked questions

Drop your PDFs, markdown, code, notebooks — **1800+ files, 39K chunks, indexed in under 3 minutes.** Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.