Skip to main content
Glama
enesjakozh
Cognitive-Stack

Hermes Search MCP Server

by Cognitive-Stack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Servidor MCP de búsqueda de Hermes 🔍

🔌 ¡ Compatible con Cline, Cursor, Claude Desktop y cualquier otro cliente MCP!

El Protocolo de Contexto de Modelo (MCP) es un estándar abierto que permite que los sistemas de IA interactúen sin problemas con diversas fuentes de datos y herramientas, lo que facilita conexiones bidireccionales seguras.

El servidor MCP de Hermes Search proporciona:

  • Capacidades de búsqueda semántica y de texto completo sobre datos estructurados y no estructurados

  • Indexación y administración de documentos en Azure Cognitive Search

  • Operaciones de búsqueda eficientes con parámetros personalizables

  • Operaciones de tipos seguros con TypeScript

Prerrequisitos 🔧

Antes de comenzar, asegúrese de tener:

  • Servicio y credenciales de Azure Cognitive Search

  • Escritorio o cursor de Claude

  • Node.js (v20 o superior)

  • Git instalado (solo es necesario si se utiliza el método de instalación Git)

Related MCP server: Azure AI Search MCP Server

Instalación del servidor MCP de Hermes Search ⚡

Corriendo con NPX

npx -y hermes-search-mcp@latest

Instalación mediante herrería

Para instalar Hermes Search MCP Server para Claude Desktop automáticamente a través de Smithery:

npx -y @smithery/cli install @hermes-search/mcp --client claude

Configuración de clientes MCP ⚙️

Configurando Cline 🤖

La forma más sencilla de configurar el servidor Hermes Search MCP en Cline es a través del mercado con un solo clic:

  1. Abrir Cline en VS Code

  2. Haga clic en el icono de Cline en la barra lateral

  3. Vaya a la pestaña "Servidores MCP" (4 cuadrados)

  4. Busca "Hermes Search" y haz clic en "instalar".

  5. Cuando se le solicite, ingrese sus credenciales de Azure Cognitive Search

Alternativamente, puede configurar manualmente el servidor Hermes Search MCP en Cline:

  1. Abra el archivo de configuración de Cline MCP:

# For macOS:
code ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

# For Windows:
code %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

  1. Agregue la configuración del servidor de búsqueda Hermes al archivo:

{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": ["-y", "hermes-search-mcp@latest"],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "your-search-endpoint",
        "AZURE_SEARCH_API_KEY": "your-api-key",
        "AZURE_SEARCH_INDEX_NAME": "your-index-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

  1. Guarde el archivo y reinicie Cline si ya está ejecutándose.

Configurando el cursor 🖥️

Nota : Requiere la versión de Cursor 0.45.6 o superior

Para configurar el servidor Hermes Search MCP en Cursor:

  1. Abrir configuración del cursor

  2. Vaya a Características > Servidores MCP

  3. Haga clic en el botón "+ Agregar nuevo servidor MCP"

  4. Complete la siguiente información:

    • Nombre : Ingrese un apodo para el servidor (por ejemplo, "hermes-search-mcp")

    • Tipo : Seleccione "comando" como tipo

    • Comando : Ingrese el comando para ejecutar el servidor: GXP5

    Importante : reemplace las variables de entorno con sus credenciales de Azure Cognitive Search

Configurando la aplicación Claude Desktop 🖥️

Para macOS:

# Create the config file if it doesn't exist
touch "$HOME/Library/Application Support/Claude/claude_desktop_config.json"

# Opens the config file in TextEdit
open -e "$HOME/Library/Application Support/Claude/claude_desktop_config.json"

Para Windows:

code %APPDATA%\Claude\claude_desktop_config.json

Agregue la configuración del servidor de búsqueda Hermes:

{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": ["-y", "hermes-search-mcp@latest"],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "your-search-endpoint",
        "AZURE_SEARCH_API_KEY": "your-api-key",
        "AZURE_SEARCH_INDEX_NAME": "your-index-name"
      }
    }
  }
}

Uso en la aplicación de escritorio Claude 🎯

Una vez completada la instalación y configurada la aplicación de escritorio de Claude, debe cerrarla por completo y volver a abrirla para ver el servidor hermes-search-mcp. Debería ver un icono de búsqueda en la esquina inferior izquierda de la aplicación, que indica las herramientas MCP disponibles.

Ejemplos de búsqueda de Hermes

  1. Buscar documentos :

Search for documents containing "machine learning" in the Azure Cognitive Search index, returning the top 10 results.

  1. Índice Contenido :

Index the following documents into Azure Cognitive Search: [{"id": "1", "title": "AI Overview", "content": "Artificial Intelligence is..."}]

  1. Eliminar índice :

Delete the current Azure Cognitive Search index.

Solución de problemas 🛠️

Problemas comunes

  1. Servidor no encontrado

    • Verifique la instalación de npm ejecutando npm --version

    • Compruebe la sintaxis de configuración de Claude Desktop

    • Asegúrese de que Node.js esté instalado correctamente ejecutando node --version

  2. Problemas con las credenciales de Azure Search

    • Confirme que sus credenciales de Azure Cognitive Search sean válidas

    • Compruebe que las credenciales estén configuradas correctamente en la configuración.

    • Verifique que no haya espacios ni comillas alrededor de las credenciales

  3. Problemas de acceso al índice

    • Verifique que el índice exista en su servicio Azure Cognitive Search

    • Comprobar los permisos del índice

    • Asegúrese de que la clave API tenga los derechos de acceso adecuados

Agradecimientos ✨

  • Protocolo de contexto de modelo para la especificación MCP

  • Antrópico para Claude Desktop

  • Microsoft Azure para búsqueda cognitiva

Available Tools

3 tools
delete-indexA

Delete the Azure Cognitive Search index

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, and the description lacks details about behavioral traits such as permanence, required permissions, or side effects. As a destructive operation, more transparency is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no extraneous words. It is concise and front-loaded with the key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete operation with no parameters or output schema, the description is minimally complete. However, it lacks context about effects or prerequisites, which would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With no parameters, the baseline is 4. The description adds minimal but adequate meaning by specifying the operation type and target, which suffices given the absence of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Delete' and the resource 'Azure Cognitive Search index', making the action unambiguous. It effectively distinguishes from sibling tools like index-content and search-documents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., when deletion is appropriate or prerequisites). The description only states the action without context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

index-contentB

Index or update documents in Azure Cognitive Search

ParametersJSON Schema
NameRequiredDescriptionDefault
documentsYesArray of documents to index

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only states 'Index or update' without explaining side effects, permissions, or whether documents are overwritten or merged. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with purpose, and is not verbose. However, it sacrifices necessary details for brevity, missing usage and behavioral context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple schema (1 param, no output schema) and lack of annotations, the description is too minimal. It fails to explain document handling (e.g., partial updates, conflict resolution) or the indexing process.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing a baseline of 3. The description repeats the schema's 'Array of documents to index' without adding extra meaning, such as required fields or document structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Index or update') and the resource ('documents in Azure Cognitive Search'), with a specific verb and resource. It distinguishes from sibling tools 'delete-index' and 'search-documents' by focusing on adding/updating.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus its siblings. There is no mention of prerequisites or alternative tools for deletion or searching, leaving the agent without context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search-documentsB

Search documents in Azure Cognitive Search index

ParametersJSON Schema
NameRequiredDescriptionDefault
topNoNumber of results to return (default: 5)
queryYesThe search query to execute
filterNoOData filter expression
selectNoFields to include in the results

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description does not disclose behavioral traits like pagination, relevance scoring, access requirements, or result format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise. However, it is somewhat underspecified for a search tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description is too minimal. It does not explain search behavior, result structure, or how parameters interact, leaving significant gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (Search) and resource (documents in Azure Cognitive Search index), and distinguishes from sibling tools (delete-index, index-content) which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. No mention of prerequisites, limitations, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observeddelete-index
    • First observedindex-content
    • First observedsearch-documents
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct operation: deleting an index, indexing content, and searching documents. No overlap in purpose.

Naming Consistency5/5

All tools follow a consistent verb-noun pattern with hyphens (delete-index, index-content, search-documents), making them predictable.

Tool Count4/5

Three tools is on the low side but covers the core search lifecycle (index, search, delete). Slightly under but reasonable for a focused MCP server.

Completeness3/5

Missing critical operations like creating an index or listing indexes. The server assumes an existing index, limiting its standalone usability.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches