Provides tools for Elasticsearch cluster health check, index management (create, delete, list), document CRUD (index, get, update, delete), and search operations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Elasticsearch MCP Server check Elasticsearch cluster health"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Elasticsearch MCP 服务器，支持 Claude Code、VSCode (Cline)、Cursor 等工具。
npm install -g es-mcp-serverRelated MCP server: Elastic MCP
变量 | 说明 | 默认值 |
| ES 地址 |
|
| 用户名 | - |
| 密码 | - |
| API Key | - |
{
"mcpServers": {
"elasticsearch": {
"command": "es-mcp-server",
"env": {
"ES_HOST": "localhost:9200"
}
}
}
}路径: ~/.config/Code/User/globalStorage/hybridtalentcomputing.cline-chinese/settings/cline_chinese_mcp_settings.json
{
"mcpServers": {
"elasticsearch": {
"command": "es-mcp-server",
"env": {
"ES_HOST": "localhost:9200"
}
}
}
}{
"mcpServers": {
"elasticsearch": {
"command": "es-mcp-server",
"env": {
"ES_HOST": "localhost:9200"
}
}
}
}工具 | 说明 |
| 集群健康检查 |
| 列出所有索引 |
| 创建索引 |
| 删除索引 |
| 索引文档 |
| 获取文档 |
| 搜索文档 |
| 更新文档 |
| 删除文档 |
| 集群信息 |
{
"index": "user_info",
"query": {
"match": { "content": "总监" }
},
"size": 10
}{
"index": "products",
"document": {
"name": "iPhone",
"price": 999
}
}MIT
Get cluster information
Inputs: no named parameters.
Create a new index
Inputs: index (required), mappings, settings.
Delete a document
Inputs: id (required), index (required).
Delete an index
Inputs: index (required).
Get a document by ID
Inputs: id (required), index (required).
Check Elasticsearch cluster health
Inputs: no named parameters.
Index a document
Inputs: index (required), document (required), id.
List all indices in the cluster
Inputs: pattern.
Search documents
Inputs: index (required), from, size, query.
Update a document
Inputs: id (required), index (required), document (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Each tool has a distinct, non-overlapping purpose: cluster info/health, index CRUD, document CRUD, listing, and search. No ambiguity exists.
All tools follow a consistent 'es_verb_noun' pattern in snake_case, making them predictable and easy to understand (e.g., es_create_index, es_delete_document).
With 10 tools, the set is well-scoped for basic Elasticsearch operations. Each tool serves a specific function, and the count is neither too few nor excessive.
The tools cover essential CRUD for indices and documents, plus cluster health and search. Missing operations like bulk indexing or mapping updates are minor gaps, but core workflows are supported.
Query, explore, and manage your databases through natural conversation.
Search multiple indices, index data, and get personalized recommendations
Interact with your Google Cloud Firestore resources using natural language commands.
Ingest and search LogsLoom logs from coding agents.