Elasticsearch 7.x 的 MCP 服务器，提供与 Elasticsearch 7.x 版本的兼容性。
提供与 Elasticsearch 7.x 交互的 MCP 协议接口
支持基本的 Elasticsearch 操作（ping、info 等）
支持完整的搜索功能，包括聚合查询、突出显示、排序和其他高级功能
通过任何 MCP 客户端轻松访问 Elasticsearch 功能
Related MCP server: Elasticsearch/OpenSearch MCP Server
Python 3.10+
Elasticsearch 7.x（推荐 7.17.x）
要通过Smithery自动为 Claude Desktop 安装 Elasticsearch 7.x MCP 服务器：
npx -y @smithery/cli install @imlewc/elasticsearch7-mcp-server --client claudepip install -e .服务器需要以下环境变量：
ELASTIC_HOST ：Elasticsearch 主机地址（例如http://localhost:9200 ）
ELASTIC_USERNAME ：Elasticsearch 用户名
ELASTIC_PASSWORD ：Elasticsearch 密码
MCP_PORT ：（可选）MCP 服务器监听端口，默认 9999
创建一个.env文件并设置ELASTIC_PASSWORD ：
ELASTIC_PASSWORD=your_secure_password启动服务：
docker-compose up -d这将启动一个三节点 Elasticsearch 7.17.10 集群、Kibana 和 MCP 服务器。
您可以使用任何 MCP 客户端连接到 MCP 服务器：
from mcp import MCPClient
client = MCPClient("localhost:9999")
response = client.call("es-ping")
print(response) # {"success": true}目前支持的 MCP 方法：
es-ping ：检查 Elasticsearch 连接
es-info ：获取 Elasticsearch 集群信息
es-search ：在 Elasticsearch 索引中搜索文档
# Basic search
search_response = client.call("es-search", {
"index": "my_index",
"query": {
"match": {
"title": "search keywords"
}
},
"size": 10,
"from": 0
})# Aggregation query
agg_response = client.call("es-search", {
"index": "my_index",
"size": 0, # Only need aggregation results, no documents
"aggs": {
"categories": {
"terms": {
"field": "category.keyword",
"size": 10
}
},
"avg_price": {
"avg": {
"field": "price"
}
}
}
})# Advanced search with highlighting, sorting, and filtering
advanced_response = client.call("es-search", {
"index": "my_index",
"query": {
"bool": {
"must": [
{"match": {"content": "search term"}}
],
"filter": [
{"range": {"price": {"gte": 100, "lte": 200}}}
]
}
},
"sort": [
{"date": {"order": "desc"}},
"_score"
],
"highlight": {
"fields": {
"content": {}
}
},
"_source": ["title", "date", "price"]
})克隆存储库
安装开发依赖项
运行服务器： elasticsearch7-mcp-server
[LICENSE 文件中的许可证]
Get Elasticsearch info
| Name | Required | Description | Default |
|---|---|---|---|
| req | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the action ('Get') without explaining what 'info' entails (e.g., cluster health, node details, version), whether it's read-only or has side effects, or any rate limits or authentication needs. This leaves critical behavioral traits unspecified.
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 extremely concise at three words, with no wasted language. It's front-loaded with the core action and resource, making it easy to parse quickly.
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?
Given the complexity (1 parameter with nested object, no output schema, no annotations), the description is completely inadequate. It doesn't explain what information is returned, how to use the parameter, or behavioral aspects, leaving the agent with insufficient context to use the tool effectively.
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?
The schema has 1 parameter ('req') with 0% description coverage, and the tool description provides no information about parameters. The description doesn't explain what 'req' should contain or how to structure it, failing to compensate for the lack of schema documentation.
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 'Get Elasticsearch info' clearly states the action (get) and resource (Elasticsearch info), making the basic purpose understandable. However, it's vague about what specific information is retrieved and doesn't distinguish this tool from its sibling 'es-ping' (which likely checks connectivity) or 'es-search' (which searches data).
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?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, appropriate contexts, or exclusions. With sibling tools like 'es-ping' and 'es-search' available, the agent receives no help in choosing between them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ping Elasticsearch server
| Name | Required | Description | Default |
|---|---|---|---|
| req | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action 'ping' without explaining what that entails—whether it's a health check, connectivity test, returns status codes, or has side effects. This leaves significant gaps in understanding the tool's behavior.
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 extremely concise with just three words, front-loading the essential action and target. There is no wasted language, making it efficient and easy to parse.
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?
Given the complexity of a ping operation (which could involve network checks, authentication, or status returns), no annotations, 0% schema coverage, and no output schema, the description is inadequate. It doesn't provide enough context for an agent to understand how to use the tool effectively or what to expect in return.
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?
The schema description coverage is 0%, and the description provides no information about the single parameter 'req'. It doesn't explain what 'req' should contain, its purpose, or how it affects the ping operation, failing to compensate for the lack of schema documentation.
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 the verb 'ping' and the target resource 'Elasticsearch server', making the purpose immediately understandable. It doesn't differentiate from sibling tools like 'es-info' or 'es-search', but the action is specific enough to understand what it does.
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?
No guidance is provided on when to use this tool versus alternatives like 'es-info' or 'es-search'. The description only states what it does, not when it should be used or what context it applies to.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search documents in Elasticsearch index
| Name | Required | Description | Default |
|---|---|---|---|
| req | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action without details on permissions, rate limits, response format, or side effects. For a search tool with no annotation coverage, this is a significant gap.
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 a single, efficient sentence with no wasted words. It's appropriately sized for the basic information it conveys, though it could be more informative without losing conciseness.
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?
Given the complexity (search operation with nested object parameter), lack of annotations, no output schema, and 0% schema coverage, the description is completely inadequate. It fails to provide necessary context for correct tool invocation.
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 description coverage is 0%, and the description adds no information about the single parameter 'req' (an object). It doesn't explain what 'req' should contain, such as query fields or options, leaving parameters completely undocumented.
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 states the action ('Search') and resource ('documents in Elasticsearch index'), which gives a basic understanding of purpose. However, it lacks specificity about what kind of search (e.g., full-text, filtered) and doesn't differentiate from sibling tools like 'es-info' or 'es-ping', making it vague rather than clear.
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?
No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites, context for searching, or exclusions, leaving the agent with no usage instructions beyond the basic purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0es-infoes-pinges-searchScored across 3 tools
Each tool has a clearly distinct purpose: es-info retrieves server information, es-ping checks connectivity, and es-search performs document searches. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.
All tool names follow a consistent 'es-' prefix and underscore-separated verb pattern (es-info, es-ping, es-search). This predictable naming convention enhances readability and usability across the tool set.
With only 3 tools, the server feels thin for an Elasticsearch domain, which typically involves operations like indexing, updating, deleting, and aggregating documents. The count is too low to cover the expected scope of a database/search engine server.
The tool set is severely incomplete for Elasticsearch functionality. It lacks essential CRUD operations (e.g., create, update, delete documents), index management, and query features beyond basic search, which will likely cause agent failures in handling typical database tasks.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
A paid remote MCP for Context7 MCP docs, built to return verdicts, receipts, usage logs, and audit-r
MCP server for searching Airweave collections with natural language queries.
