MCPgee
MCPgee
MCPgeeMCPgee

Ragie

v1.0.0•Knowledge & Memory•stable

📇 ☁️ - Retrieve context from your [Ragie](https://www.ragie.ai) (RAG) knowledge base connected to integrations like Google Drive, Notion, JIRA and more.

mcpmodel-context-protocolragieknowledge-baseretrieval
Share:
86
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Ragie?

Ragie is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 📇 ☁️ - retrieve context from your [ragie](https://www.ragie.ai) (rag) knowledge base connected to integrations like google drive, notion, jira and more.

📇 ☁️ - Retrieve context from your [Ragie](https://www.ragie.ai) (RAG) knowledge base connected to integrations like Google Drive, Notion, JIRA and more.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Retrieve context from Ragie knowledge bases connected to Google Drive and Notion.
Query RAG-indexed documents for accurate information retrieval.
Integrate enterprise knowledge into AI workflows.
ragieai

Maintainer

LicenseMIT License
Languagejavascript
Versionv1.0.0
UpdatedMay 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y @ragieai/mcp-server

Manual Installation

npx -y @ragieai/mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Ragie

The Ragie MCP server connects Claude and other MCP clients to a Ragie knowledge base, enabling retrieval-augmented generation over documents synced from Google Drive, Notion, JIRA, and other integrations. It exposes a single 'retrieve' tool that performs semantic search across your indexed content, returning the most relevant document chunks to ground AI responses in your organization's actual data. Teams use it to give Claude accurate, up-to-date access to internal documentation, wikis, and business data without manually pasting content into the chat.

Prerequisites

  • A Ragie account with an active knowledge base at ragie.ai
  • A Ragie API key (RAGIE_API_KEY) from the Ragie dashboard
  • Node.js 18 or later installed (for npx execution)
  • An MCP-compatible client such as Claude Desktop
1

Create a Ragie account and set up a knowledge base

Sign up at ragie.ai, create a knowledge base, and connect at least one integration (Google Drive, Notion, JIRA, or upload documents directly). Wait for the initial indexing to complete.

2

Retrieve your Ragie API key

In the Ragie dashboard, navigate to Settings and copy your API key. This key authenticates the MCP server to your knowledge base.

3

Test the server from the command line

Run the server directly with your API key to verify connectivity before wiring it into your MCP client.

RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server
4

Configure your MCP client

Add the Ragie MCP server to your Claude Desktop configuration with the API key and optional partition ID.

5

Query your knowledge base through Claude

Ask Claude questions about your connected documents. It will call the 'retrieve' tool automatically, fetch the most relevant chunks, and synthesize an answer grounded in your real content.

Ragie Examples

Client configuration

Add the Ragie MCP server to Claude Desktop with your API key. Use the optional --partition flag to scope retrieval to a specific knowledge base partition.

{
  "mcpServers": {
    "ragie": {
      "command": "npx",
      "args": ["-y", "@ragieai/mcp-server", "--partition", "your_partition_id"],
      "env": {
        "RAGIE_API_KEY": "your_ragie_api_key"
      }
    }
  }
}

Prompts to try

Example prompts that trigger the retrieve tool against your Ragie knowledge base.

- "What is our company's vacation policy according to the HR handbook?"
- "Find the API rate limits documented in our internal developer guide"
- "Summarize the Q3 project status updates from the last team meeting notes"
- "What does our architecture decision record say about the choice of database?"
- "Search for any documentation about the onboarding process for new engineers"

Troubleshooting Ragie

Retrieve tool returns empty results for queries that should match documents

Verify that your knowledge base has finished indexing in the Ragie dashboard. Newly connected integrations can take minutes to hours to fully index. Also confirm the partition ID matches the correct knowledge base partition.

Authentication error: 401 Unauthorized when starting the server

Double-check that RAGIE_API_KEY is set correctly in the MCP server env block. API keys are partition-scoped in some Ragie plans — confirm the key matches the partition you are querying.

Answers from Claude seem outdated even after updating documents in Google Drive

Ragie syncs integrations on a schedule. In the Ragie dashboard, trigger a manual re-sync for the affected integration, then wait for re-indexing to complete before retrying.

Frequently Asked Questions about Ragie

What is Ragie?

Ragie is a Model Context Protocol (MCP) server that 📇 ☁️ - retrieve context from your [ragie](https://www.ragie.ai) (rag) knowledge base connected to integrations like google drive, notion, jira and more. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ragie?

Install via npm with the command: npx -y @ragieai/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Ragie?

Ragie works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Ragie free to use?

Yes, Ragie is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Ragie Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Ragie? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "ragie-model-context-protocol-server": { "command": "npx", "args": ["-y", "@ragieai/mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Ragie?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides