Ragie Model Context Protocol Server
Servidor de protocolo de contexto del modelo Ragie
Un servidor de Protocolo de Contexto de Modelo (MCP) que proporciona acceso a las capacidades de recuperación de la base de conocimientos de Ragie.
Descripción
Este servidor implementa el Protocolo de Contexto de Modelo para que los modelos de IA puedan recuperar información de una base de conocimiento de Ragie. Proporciona una herramienta única llamada "retrieve" que permite consultar la base de conocimiento para obtener información relevante.
Related MCP server: RAG Information Retriever
Prerrequisitos
Node.js >= 18
Una clave API de Ragie
Instalación
El servidor requiere la siguiente variable de entorno:
RAGIE_API_KEY(obligatorio): Su clave de autenticación de la API de Ragie
El servidor se iniciará y escuchará en stdio los mensajes del protocolo MCP.
Instalar y ejecutar el servidor con npx:
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-serverOpciones de línea de comandos
El servidor admite las siguientes opciones de línea de comandos:
--description, -d <text>: Anula la descripción de la herramienta predeterminada con texto personalizado--partition, -p <id>: Especifique el ID de la partición Ragie para consultar
Ejemplos:
# 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_idConfiguración del cursor
Para utilizar este servidor MCP con Cursor:
Opción 1: Crear un archivo de configuración MCP
Guarde un archivo llamado
mcp.json
Para las herramientas específicas de un proyecto , cree un archivo
.cursor/mcp.jsonen el directorio del proyecto. Esto le permite definir servidores MCP que solo estén disponibles dentro de ese proyecto específico.Para las herramientas que desee usar en todos los proyectos , cree un archivo
~/.cursor/mcp.jsonen su directorio personal. Esto hará que los servidores MCP estén disponibles en todos sus espacios de trabajo de Cursor.
Ejemplo mcp.json :
{
"mcpServers": {
"ragie": {
"command": "npx",
"args": [
"-y",
"@ragieai/mcp-server",
"--partition",
"optional_partition_id"
],
"env": {
"RAGIE_API_KEY": "your_api_key"
}
}
}
}Opción 2: utilizar un script de shell
Guarde un archivo llamado
ragie-mcp.shen su sistema:
#!/usr/bin/env bash
export RAGIE_API_KEY="your_api_key"
npx -y @ragieai/mcp-server --partition optional_partition_idDar permisos de ejecución al archivo:
chmod +x ragie-mcp.shAgregue el script del servidor MCP yendo a Configuración -> Configuración del cursor -> Servidores MCP en la interfaz de usuario del cursor.
Reemplace your_api_key con su clave API de Ragie real y, opcionalmente, configure el ID de la partición si es necesario.
Configuración del escritorio de Claude
Para utilizar este servidor MCP con el escritorio Claude:
Cree el archivo de configuración MCP
claude_desktop_config.json:
Para MacOS: utilice
~/Library/Application Support/Claude/claude_desktop_config.jsonPara Windows: utilice
%APPDATA%/Claude/claude_desktop_config.json
Ejemplo claude_desktop_config.json :
{
"mcpServers": {
"ragie": {
"command": "npx",
"args": [
"-y",
"@ragieai/mcp-server",
"--partition",
"optional_partition_id"
],
"env": {
"RAGIE_API_KEY": "your_api_key"
}
}
}
}Reemplace your_api_key con su clave API de Ragie real y, opcionalmente, configure el ID de la partición si es necesario.
Reinicie el escritorio de Claude para que los cambios surtan efecto.
La herramienta de recuperación de Ragie ahora estará disponible en tus conversaciones de escritorio de Claude.
Características
Herramienta de recuperación
El servidor proporciona una herramienta retrieve que permite buscar en la base de conocimientos. Acepta los siguientes parámetros:
query(cadena): La consulta de búsqueda para encontrar información relevante
La herramienta devuelve:
Una matriz de fragmentos de contenido que contienen texto coincidente de la base de conocimientos
Desarrollo
Este proyecto está escrito en TypeScript y utiliza las siguientes dependencias principales:
@modelcontextprotocol/sdk: Para implementar el servidor MCPragie: Para interactuar con la API de Ragiezod: Para la validación de tipos en tiempo de ejecución
Configuración de desarrollo
Ejecutando el servidor en modo de desarrollo:
RAGIE_API_KEY=your_api_key npm run dev -- --partition optional_partition_idConstruyendo el proyecto:
npm run buildLicencia
Licencia MIT: consulte LICENSE.txt para obtener más detalles.
Available Tools
1 toolretrieveA
Look up information in the Knowledge Base. Use this tool when you need to:
Find relevant documents or information on specific topics
Retrieve company policies, procedures, or guidelines
Access product specifications or technical documentation
Get contextual information to answer company-specific questions
Find historical data or information about projects
| Name | Required | Description | Default |
|---|---|---|---|
| topK | No | The maximum number of results to return. Defaults to 8. | |
| query | Yes | The query to search for data in the Knowledge Base | |
| filter | No | The metadata search filter on documents. Returns chunks only from documents which match the filter. The following filter operators are supported: $eq - Equal to (number, string, boolean), $ne - Not equal to (number, string, boolean), $gt - Greater than (number), $gte - Greater than or equal to (number), $lt - Less than (number), $lte - Less than or equal to (number), $in - In array (string or number), $nin - Not in array (string or number). The operators can be combined with AND and OR. Read Metadata & Filters guide for more details and examples. | |
| rerank | No | Whether to try and find only the most relevant data. Defaults to false. | |
| recencyBias | No | Whether to favor data towards more recent documents. Defaults to false. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only implies a read-only operation by saying 'Look up information', but fails to explicitly state it is read-only, does not disclose authentication needs, rate limits, or error behavior. This is a significant gap for a retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise, using a bullet list of use cases. It is front-loaded with the purpose statement. However, some redundancy exists with 'Use this tool when you need to' repeated for each item.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 5 parameters, including a complex nested filter object, and no output schema. The description does not explain the return format, pagination, or how results are structured. It only vaguely mentions 'information', leaving the agent without sufficient context to interpret the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and all parameters have descriptions in the schema. The tool description does not add additional meaning beyond what the schema provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Look up information in the Knowledge Base' and lists specific use cases (e.g., 'Find relevant documents', 'Retrieve company policies'). It directly addresses what the tool does with a specific verb and resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a bullet list of when to use the tool, such as 'Find relevant documents or information' and 'Get contextual information'. It implicitly guides usage but does not explicitly state when not to use or mention alternatives, though no sibling tools exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no potential for confusion between tools. The tool's purpose is clearly defined.
With a single tool named 'retrieve', there is no pattern to evaluate. Naming is neither consistent nor inconsistent—it's neutral.
A knowledge base server with only one retrieval tool is extremely minimal. Agents cannot perform any CRUD operations, making this count far too low for the implied scope.
The server only supports retrieval. Essential actions like adding, updating, or deleting documents are missing, leaving significant gaps in functionality.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
An MCP server that integrates with Discord to provide AI-powered features.
MCP server for AI dialogue using various LLM models via AceDataCloud
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseBqualityFmaintenanceAn MCP server that enables users to retrieve information from AWS Knowledge Bases using RAG (Retrieval-Augmented Generation) via Bedrock Agent Runtime.1309MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses.
- AlicenseNot gradedqualityBmaintenanceRAG Knowledge - MCP server providing AI-powered tools and automation by MEOK AI Labs13MIT
- AlicenseNot gradedqualityBmaintenanceA plugin-based MCP server that enables AI assistants to interact with external systems through custom tools, resources, and prompts.4AGPL 3.0
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ragieai/ragie-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server