ElasticsearchMCP Server

1. Open your agent's MCP configuration file.
2. Merge the snippet below into it, filling in the environment variables with your own values.
3. Restart the agent — the "Elasticsearch" tools will be available.

{
  "mcpServers": {
    "elasticsearch": {
      "command": "npx",
      "args": [
        "-y",
        "@elastic/mcp-server-elasticsearch"
      ],
      "env": {
        "ES_URL": "https://localhost:9200",
        "ES_API_KEY": "your-api-key"
      }
    }
  }
}

1. In ChatGPT, open Settings → Connectors → Advanced and enable Developer mode.
2. Click Create and add the server's remote URL (SSE or streamable HTTP endpoint).
3. Enable the connector in a conversation to use its tools.

Note: ChatGPT only supports remote MCP servers. If this server runs locally via a command, you'll need to host it behind an HTTP endpoint first — check the repository for a hosted option.

{
  "command": "npx",
  "args": [
    "-y",
    "@elastic/mcp-server-elasticsearch"
  ],
  "env": {
    "ES_URL": "https://localhost:9200",
    "ES_API_KEY": "your-api-key"
  }
}

{
  "command": "npx",
  "args": [
    "-y",
    "@elastic/mcp-server-elasticsearch"
  ],
  "env": {
    "ES_URL": "https://localhost:9200",
    "ES_API_KEY": "your-api-key"
  }
}

{
  "command": "npx",
  "args": [
    "-y",
    "@elastic/mcp-server-elasticsearch"
  ],
  "env": {
    "ES_URL": "https://localhost:9200",
    "ES_API_KEY": "your-api-key"
  }
}