Skip to content
Back to search

ragie-mcp-server

Ragie Model Context Protocol Server

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ragieai--ragie-mcp-server/badge.svg)](/listings/ragieai--ragie-mcp-server)

HTML

<a href="/listings/ragieai--ragie-mcp-server"><img src="/api/listings/ragieai--ragie-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

The server requires the following environment variable:

- `RAGIE_API_KEY` (required): Your Ragie API authentication key

The server will start and listen on stdio for MCP protocol messages.

Install and run the server with npx:

RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server

Command Line Options

The server supports the following command line options:

- `--description, -d <text>`: Override the default tool description with custom text - `--partition, -p <id>`: Specify the Ragie partition ID to query

Examples:

# With custom description
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base for information"

# With partition specified
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --partition your_partition_id

# Using both options
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base" --partition your_partition_id

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 178 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # IMPORTANT!
  2. *This project is no longer needed*. Ragie now supports MCP natively as a streamable HTTP server. See docs here: [https://docs.ragie.ai/docs/mcp-overview]
  3. If you would like users within your company to be able to access you knowledge base in applications like Claude or ChatGPT, you may need [MCP Bridge](https://www.ragie.ai/mcp-bridge)
  4. ![image](https://github.com/user-attachments/assets/75e80f87-f39e-4f10-8c97-bbc848bbed82)
  5. # Ragie Model Context Protocol Server
  6. A Model Context Protocol (MCP) server that provides access to Ragie's knowledge base retrieval capabilities.
  7. ## Description
  8. This server implements the Model Context Protocol to enable AI models to retrieve information from a Ragie knowledge base. It provides a single tool called "retrieve" that allows querying the knowledge base for relevant information.
  9. ## Prerequisites
  10. - Node.js >= 18
  11. - A Ragie API key
  12. ## Installation
  13. The server requires the following environment variable:
  14. - `RAGIE_API_KEY` (required): Your Ragie API authentication key
  15. The server will start and listen on stdio for MCP protocol messages.
  16. Install and run the server with npx:
  17. ```bash
  18. RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server
  19. ```
  20. ### Command Line Options
  21. The server supports the following command line options:
  22. - `--description, -d <text>`: Override the default tool description with custom text
  23. - `--partition, -p <id>`: Specify the Ragie partition ID to query
  24. Examples:
  25. ```bash
  26. # With custom description
  27. RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base for information"
  28. # With partition specified
  29. RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --partition your_partition_id
  30. # Using both options
  31. RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base" --partition your_partition_id
  32. ```
  33. ## Cursor Configuration
  34. To use this MCP server with Cursor:
  35. ### Option 1: Create an MCP configuration file
  36. 1. Save a file called `mcp.json`
  37. * **For tools specific to a project**, create a `.cursor/mcp.json` file in your project directory. This allows you to define MCP servers that are only available within that specific project.
  38. * **For tools that you want to use across all projects**, create a `~/.cursor/mcp.json` file in your home directory. This makes MCP servers available in all your Cursor workspaces.
  39. Example `mcp.json`:
  40. ```json
  41. {
  42. "mcpServers": {
  43. "ragie": {
  44. "command": "npx",
  45. "args": [
  46. "-y",
  47. "@ragieai/mcp-server",
  48. "--partition",
  49. "optional_partition_id"
  50. ],
  51. "env": {
  52. "RAGIE_API_KEY": "your_api_key"
  53. }
  54. }
  55. }
  56. }
  57. ```
  58. ### Option 2: Use a shell script
  59. 1. Save a file called `ragie-mcp.sh` on your system:
  60. ```bash
  61. #!/usr/bin/env bash
  62. export RAGIE_API_KEY="your_api_key"
  63. npx -y @ragieai/mcp-server --partition optional_partition_id
  64. ```
  65. 2. Give the file execute permissions: `chmod +x ragie-mcp.sh`
  66. 3. Add the MCP server script by going to **Settings** -> **Cursor Settings** -> **MCP Servers** in the Cursor UI.
  67. Replace `your_api_key` with your actual Ragie API key and optionally set the partition ID if needed.
  68. ## Claude Desktop Configuration
  69. To use this MCP server with Claude desktop:
  70. 1. Create the MCP config file `claude_desktop_config.json`:
  71. * For MacOS: Use `~/Library/Application Support/Claude/claude_desktop_config.json`
  72. * For Windows: Use `%APPDATA%/Claude/claude_desktop_config.json`
  73. Example `claude_desktop_config.json`:
  74. ```json
  75. {
  76. "mcpServers": {
  77. "ragie": {
  78. "command": "npx",
  79. "args": [
  80. "-y",
  81. "@ragieai/mcp-server",
  82. "--partition",
  83. "optional_partition_id"
  84. ],
  85. "env": {
  86. "RAGIE_API_KEY": "your_api_key"
  87. }
  88. }
  89. }
  90. }
  91. ```
  92. Replace `your_api_key` with your actual Ragie API key and optionally set the partition ID if needed.
  93. 2. Restart Claude desktop for the changes to take effect.
  94. The Ragie retrieval tool will now be available in your Claude desktop conversations.
  95. ## Features
  96. ### Retrieve Tool
  97. The server provides a `retrieve` tool that can be used to search the knowledge base. It accepts the following parameters:
  98. - `query` (string): The search query to find relevant information
  99. - `topK` (number, optional, default: 8): The maximum number of results to return
  100. - `rerank` (boolean, optional, default: true): Whether to try and find only the most relevant information
  101. - `recencyBias` (boolean, optional, default: false): Whether to favor results towards more recent information
  102. The tool returns:
  103. - An array of content chunks containing matching text from the knowledge base
  104. ## Development
  105. This project is written in TypeScript and uses the following main dependencies:
  106. - `@modelcontextprotocol/sdk`: For implementing the MCP server
  107. - `ragie`: For interacting with the Ragie API
  108. - `zod`: For runtime type validation
  109. ### Development setup
  110. Running the server in dev mode:
  111. ```bash
  112. RAGIE_API_KEY=your_api_key npm run dev -- --partition optional_partition_id
  113. ```
  114. Building the project:
  115. ```bash
  116. npm run build
  117. ```
  118. ## License
  119. MIT License - See LICENSE.txt for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.