LABSCO SUMMARY

Reads and writes the same index.

Most search connectors are read-only; this one indexes too, which means an assistant can add what it found to the corpus it searches. That also raises the stakes on the key you give it — deleting the index is one of the operations, so a scoped key is the right call for anything shared. The index name is fixed in the environment, so one server instance serves one index.

What it is

A TypeScript MCP server over Azure Cognitive Search. It covers both directions: querying an index with customizable parameters, and putting documents into one — so an assistant can search a corpus and add to it in the same session.

What you get

Full-text and semantic search over structured and unstructured data in your index, with a result count you control
Document indexing — hand it records with their fields and they go into the Azure Cognitive Search index
Index management, including deleting the current index
Type-safe operations throughout, since the server is written in TypeScript

Requirements

An Azure Cognitive Search service and three environment variables: AZURE_SEARCH_ENDPOINT, AZURE_SEARCH_API_KEY and AZURE_SEARCH_INDEX_NAME. Node.js v20 or higher. Run it with npx -y hermes-search-mcp@latest, or install it into Cline from the marketplace. The API key needs rights for what you intend to do — search-only keys will not index. The package is hermes-search-mcp (1.0.1 in package.json).

Setup effort

One command plus a key — npx -y hermes-search-mcp@latest, then supply credentials

See installation options

USE CASES

01

Searching a company knowledge base from the assistant

Query the index in natural language and cap the number of results, without building a search UI.

02

Adding new material to the corpus

Hand the server the documents with their fields and let it index them into Azure Cognitive Search.

03

Rebuilding an index during development

Delete the current index and re-index a fresh set of documents while iterating on the schema.

BEFORE YOU INSTALL

What to know first

Requires

npx on PATH
Node.js
AZURE_SEARCH_API_KEY in your environment

Where it runs

Both documented clients run the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

npx -y hermes-search-mcp@latest

MCP Clients

Cline

CLINE · JSON

{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hermes-search-mcp@latest"
      ],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "<YOUR_AZURE_SEARCH_ENDPOINT>",
        "AZURE_SEARCH_API_KEY": "<YOUR_AZURE_SEARCH_API_KEY>",
        "AZURE_SEARCH_INDEX_NAME": "<YOUR_AZURE_SEARCH_INDEX_NAME>"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hermes-search-mcp@latest"
      ],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "<YOUR_AZURE_SEARCH_ENDPOINT>",
        "AZURE_SEARCH_API_KEY": "<YOUR_AZURE_SEARCH_API_KEY>",
        "AZURE_SEARCH_INDEX_NAME": "<YOUR_AZURE_SEARCH_INDEX_NAME>"
      }
    }
  }
}

Hermes Search