API 规范
本项目基于 Elastic Kibana 官方 API 文档，并使用 Elastic Stack 8.x (ES8) 的 OpenAPI YAML 规范来动态检索和管理所有 Kibana API 端点。如需了解最新详情，请参阅Kibana API 文档。
Kibana MCP 服务器实现允许任何与 MCP 兼容的客户端（例如 Claude Desktop）通过自然语言或编程请求访问您的 Kibana 实例。
该项目由社区维护，不是 Elastic 或 MCP 的官方产品。
连接到本地或远程 Kibana 实例
安全认证（用户名/密码）
SSL/TLS 和自定义 CA 证书支持
将 Kibana API 端点公开为工具和资源
从 MCP 客户端搜索、查看和执行 Kibana API
类型安全、可扩展且易于集成
Related MCP server: mshegolev/kibana-mcp
├── index.ts # Server entry point
├── src/
│ ├── types.ts # Type definitions and schemas
│ ├── base-tools.ts # Tool registration and API logic
│ ├── prompts.ts # Prompt registration (expert & resource helper)
│ └── resources.ts # Resource registration (API paths/URIs)
├── kibana-openapi-source.yaml # Kibana API OpenAPI index
├── README.md # English documentation
├── README_zh.md # Chinese documentation资源 URI | 描述 |
| 返回所有可用的 Kibana API 端点（可以使用 |
| 返回特定 API 端点的详细信息 |
例子：
kibana-api://paths?search=saved_objects
kibana-api://path/GET/%2Fapi%2Fstatus
工具名称 | 描述 | 输入参数 |
| 获取 Kibana 服务器的当前状态 | 没有任何 |
| 执行自定义 Kibana API 请求 |
|
| 按关键字搜索 Kibana API 端点 |
|
| 列出所有 Kibana API 端点 | 没有任何 |
| 获取特定 Kibana API 端点的详细信息 |
|
提示名称 | 描述 |
| 工具专家模式（强烈推荐在 Claude Desktop 中使用），支持通过工具对 Kibana API 进行智能分析、搜索、执行和解释。推荐大多数用户使用。 |
| 资源助手模式，指导如何通过资源 URI 访问和使用 Kibana API 信息。适用于仅支持资源访问或需要原始 API 元数据的客户端。 |
通过环境变量配置服务器：
变量名称 | 描述 | 必需的 |
| Kibana 服务器地址（例如http://localhost:5601 ） | 是的 |
| Kibana 用户名 | 是的 |
| Kibana 密码 | 是的 |
| CA 证书路径（可选，用于 SSL 验证） | 不 |
| 请求超时（毫秒）（默认 30000） | 不 |
| 最大请求重试次数（默认 3 次） | 不 |
| 设置为 | 不 |
KIBANA_URL=http://your-kibana-server:5601 \
KIBANA_USERNAME=your-username \
KIBANA_PASSWORD=your-password \
NODE_TLS_REJECT_UNAUTHORIZED=0 \
npm start添加到 Claude Desktop 配置文件（MacOS 路径： ~/Library/Application Support/Claude/claude_desktop_config.json ）：
{
"mcpServers": {
"kibana-mcp-server": {
"command": "node",
"args": ["/path/to/mcp-server-kibana/dist/index.js"],
"env": {
"KIBANA_URL": "http://your-kibana-server:5601",
"KIBANA_USERNAME": "your-username",
"KIBANA_PASSWORD": "your-password",
"NODE_TLS_REJECT_UNAUTHORIZED": "0"
}
}
}
}“我的 Kibana 服务器状态如何？”
“列出所有可用的 Kibana API 端点。”
“显示 POST /api/saved_objects/_find 端点的详细信息。”
“对 /api/status 执行自定义 API 请求。”
“获取 Kibana 中所有仪表板的列表。”
“查询与端点事件相关的 API 端点。”
“列出所有与案件相关的 API 端点。”
“在 Kibana 中创建新案例。”
“在 Kibana 中创建一个新的仪表板。”
当将此服务器与 Claude Desktop 一起使用时，支持两种不同的提示交互模式：
工作原理： Claude Desktop 可以直接调用服务器工具（例如get_status 、 execute_api 、 search_kibana_api_paths等）来回答您的问题或执行操作。
**最适合：**需要对话式引导式体验的用户。服务器将自动搜索、执行并解释 Kibana API。
示例： “显示与已保存对象相关的所有 Kibana API 端点。”
**测试提示：**选择Claude Desktop中的kibana-tool-expert提示进行集成测试，然后开始使用它。
工作原理： Claude Desktop 通过资源 URI（例如kibana-api://paths或kibana-api://path/GET/%2Fapi%2Fstatus ）与服务器交互，服务器返回结构化数据供 Claude 解析。
**最适合：**高级用户、仅支持资源访问的 MCP 客户端或需要原始 API 元数据的编程场景。
示例： “获取资源 kibana-api://paths?search=dashboard”
注意： resources中的两个端点（ kibana-api://paths和kibana-api://path/{method}/{encoded_path} ）都有对应的基础工具（ list_all_kibana_api_paths 、 get_kibana_api_detail ）。这样的设计确保了与无法智能选择多个资源的 MCP 客户端兼容，从而让 Claude Desktop 等工具更容易与 Kibana 交互。
**提示：**建议大多数用户使用工具模式以获得更自然、更强大的体验；资源模式为高级和兼容性用例提供了最大的灵活性。
安装依赖项：
npm install构建服务器：
npm run build在开发模式下自动重建：
npm run watch由于 MCP 服务器通过 stdio 进行通信，调试可能不太方便。建议使用 MCP Inspector：
npm run inspector启动后，Inspector会提供一个浏览器可以访问的调试工具URL。
本项目由社区维护。欢迎贡献和反馈！请在所有沟通中保持尊重和包容的态度，并遵守Elastic 社区行为准则。
本项目遵循 Apache License 2.0 许可协议。详情请参阅LICENSE文件。
检查MCP配置是否正确
确保 Kibana 地址可以访问
验证身份验证凭据是否具有足够的权限
如果使用自定义 CA，请确保证书路径正确且可读
如果使用NODE_TLS_REJECT_UNAUTHORIZED=0 ，请注意安全风险
检查终端输出的错误消息
Execute a custom API request for Kibana with multi-space support
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | ||
| method | Yes | ||
| params | No | ||
| path | Yes | ||
| space | No | Target Kibana space (optional, defaults to configured space) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'multi-space support' which adds some context about space handling, but fails to describe critical behaviors like authentication requirements, rate limits, error handling, or what 'execute' entails (e.g., whether it's idempotent, what happens on failure). For a tool that can perform write operations (PUT, DELETE), this is inadequate.
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 that front-loads the core purpose ('Execute a custom API request for Kibana') and adds a key feature ('with multi-space support'). There's no wasted language or redundancy.
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 (5 parameters, no output schema, no annotations, and support for write operations), the description is incomplete. It lacks information about return values, error conditions, authentication, and how to use parameters effectively. The mention of 'multi-space support' is helpful but insufficient for a tool with this scope and potential impact.
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 only 20% (only the 'space' parameter has a description), so the description must compensate. It adds minimal value by implying the tool handles 'multi-space' contexts, which relates to the 'space' parameter, but doesn't explain other parameters like 'body', 'params', 'method', or 'path' beyond what the schema provides. The baseline is 3 since schema coverage is low but the description doesn't fully compensate.
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 ('execute') and resource ('custom API request for Kibana'), specifying the action and target. However, it doesn't explicitly differentiate from siblings like 'get_kibana_api_detail' or 'list_all_kibana_api_paths', which appear to be read-only operations, while this tool supports multiple HTTP methods including write operations.
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?
The description mentions 'multi-space support' but doesn't provide explicit guidance on when to use this tool versus alternatives. No context is given about prerequisites, when-not-to-use scenarios, or comparisons to sibling tools like 'get_available_spaces' or 'search_kibana_api_paths'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all available Kibana spaces with current context
| Name | Required | Description | Default |
|---|---|---|---|
| include_details | No | Include detailed space information (name, description, etc.) |
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 states what the tool does but lacks details on permissions needed, rate limits, pagination, or what 'current context' entails. This is a significant gap for a tool that likely interacts with a Kibana API.
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 that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, 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 no annotations and no output schema, the description is incomplete. It doesn't explain what 'available spaces' means, what 'current context' includes, or what the return values look like. For a tool that likely returns a list of Kibana spaces, more context is needed to guide the agent 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 description coverage is 100%, so the input schema already documents the 'include_details' parameter. The description doesn't add any parameter-specific information beyond what's in the schema, such as examples or edge cases, but the baseline is 3 when the schema does the heavy lifting.
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 'Get' and the resource 'all available Kibana spaces with current context', making the purpose understandable. However, it doesn't explicitly differentiate this tool from its siblings like 'list_all_kibana_api_paths' or 'search_kibana_api_paths', which might also involve listing Kibana resources.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or compare it to sibling tools like 'list_all_kibana_api_paths', leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get details for a specific Kibana API endpoint
| Name | Required | Description | Default |
|---|---|---|---|
| method | Yes | HTTP method, e.g. GET, POST, PUT, DELETE | |
| path | Yes | API path, e.g. /api/actions/connector_types |
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 states what the tool does but doesn't describe how it behaves—such as whether it's read-only, what format the details are returned in, error handling, or any rate limits. This is a significant gap for a tool with no annotation coverage.
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 that directly states the tool's purpose without any fluff. It's appropriately sized and front-loaded, 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 of querying API endpoints and the lack of annotations and output schema, the description is insufficient. It doesn't explain what 'details' include, how results are structured, or any behavioral aspects like safety or performance, leaving the agent with incomplete information for proper use.
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 100%, with both parameters ('method' and 'path') well-documented in the schema. The description adds no additional meaning beyond implying that these parameters identify a specific endpoint, which is already clear from the schema. This meets the baseline for high schema coverage.
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 ('Get details') and resource ('specific Kibana API endpoint'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'list_all_kibana_api_paths' or 'search_kibana_api_paths' which also deal with Kibana API endpoints, so it doesn't fully distinguish itself from alternatives.
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?
The description provides no guidance on when to use this tool versus alternatives like 'list_all_kibana_api_paths' or 'execute_kb_api'. It doesn't mention prerequisites, context, or exclusions, leaving the agent to infer usage based on the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Kibana server status with multi-space support
| Name | Required | Description | Default |
|---|---|---|---|
| space | No | Target Kibana space (optional, defaults to configured space) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states what the tool does but lacks behavioral details: it doesn't specify if this is a read-only operation, what permissions are required, whether it affects system state, rate limits, or what the output format looks like (e.g., JSON structure, error handling). For a tool with no annotation coverage, this is a significant gap in transparency.
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 that front-loads the core purpose ('Get Kibana server status') and adds a key feature ('with multi-space support'). There is no wasted verbiage, and it's appropriately sized for a simple tool with one optional parameter.
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 tool's low complexity (1 optional parameter, no output schema, no annotations), the description is minimally complete. It covers the basic purpose but lacks context on usage guidelines, behavioral traits, or output details. For a status-checking tool, it should ideally mention what 'status' entails (e.g., health metrics, version info) or how it differs from siblings, but it's adequate as a starting point.
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 100%, with the single parameter 'space' documented in the schema as optional and defaulting to configured space. The description adds minimal value beyond this by mentioning 'multi-space support', which implies the parameter's purpose but doesn't provide additional syntax or format details. Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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 ('Get') and resource ('Kibana server status'), making the purpose evident. It adds specificity with 'multi-space support' which distinguishes it from generic status tools. However, it doesn't explicitly differentiate from sibling tools like 'get_kibana_api_detail' or 'execute_kb_api', which might also retrieve status-related information.
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?
The description provides no guidance on when to use this tool versus alternatives. It mentions 'multi-space support' but doesn't explain if this is for checking overall server health, space-specific status, or when to prefer it over siblings like 'get_available_spaces' or 'execute_kb_api'. No explicit when/when-not instructions or prerequisites are included.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all Kibana API endpoints as a resource list
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't describe important behavioral traits like whether this is a read-only operation, what format the resource list returns, whether there are rate limits, or if authentication is required. The description is functional but lacks operational context.
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 that communicates the core functionality without any wasted words. It's appropriately sized for a zero-parameter tool and front-loads the essential information ('List all Kibana API endpoints').
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?
For a zero-parameter tool with no output schema, the description adequately states what the tool does but lacks important context about the return format, behavioral characteristics, and differentiation from sibling tools. Given the complexity of API endpoint listing and the absence of annotations/output schema, the description should provide more operational guidance to be truly complete.
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 tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, and the schema fully documents this absence without needing additional explanation in the description.
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 action ('List all') and resource ('Kibana API endpoints as a resource list'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'search_kibana_api_paths' or 'get_kibana_api_detail', which would require more specific scope information.
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?
The description provides no guidance on when to use this tool versus alternatives like 'search_kibana_api_paths' or 'get_kibana_api_detail'. There's no mention of use cases, prerequisites, or comparisons with sibling tools, leaving the agent without contextual usage information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Kibana API endpoints by keyword
| Name | Required | Description | Default |
|---|---|---|---|
| search | Yes | Search keyword for filtering API endpoints |
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 states the tool searches endpoints by keyword, but doesn't describe behavioral traits such as whether it's read-only, safe to use, what the output format looks like (e.g., list of paths, details), or any limitations (e.g., search scope, rate limits). For a tool with zero annotation coverage, this is a significant gap in transparency.
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: 'Search Kibana API endpoints by keyword'. It's front-loaded with the core action and resource, with zero wasted words. Every part of the sentence earns its place by conveying essential purpose, making it highly concise and well-structured.
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 tool's complexity (a search function with one parameter) and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a list of endpoint paths, details, or matches), how results are formatted, or any behavioral context needed for effective use. This leaves significant gaps for the agent to understand the tool's full context.
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 input schema has 100% description coverage, with the single parameter 'search' documented as 'Search keyword for filtering API endpoints'. The description adds no additional meaning beyond this, as it only repeats the keyword concept without elaborating on syntax, format, or examples. Given the high schema coverage, the baseline score of 3 is appropriate, as the schema does the heavy lifting.
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 tool's purpose: 'Search Kibana API endpoints by keyword'. It specifies the verb ('search'), resource ('Kibana API endpoints'), and mechanism ('by keyword'), which is specific and actionable. However, it doesn't explicitly differentiate from sibling tools like 'list_all_kibana_api_paths' or 'get_kibana_api_detail', which prevents a perfect score.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_all_kibana_api_paths' (which might list all endpoints without filtering) or 'get_kibana_api_detail' (which might retrieve details for a specific endpoint), leaving the agent to infer usage context. This lack of explicit when-to-use or alternative references results in minimal guidance.
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.
v1.0.0execute_kb_apiget_available_spacesget_kibana_api_detailget_statuslist_all_kibana_api_pathssearch_kibana_api_pathsScored across 6 tools
Each tool has a clearly distinct purpose with no overlap: execute_kb_api performs custom API calls, get_available_spaces lists spaces, get_kibana_api_detail provides endpoint details, get_status checks server status, list_all_kibana_api_paths enumerates all endpoints, and search_kibana_api_paths searches endpoints. The descriptions reinforce these unique functions, making misselection unlikely.
All tools follow a consistent verb_noun pattern with snake_case: execute_kb_api, get_available_spaces, get_kibana_api_detail, get_status, list_all_kibana_api_paths, and search_kibana_api_paths. The naming is predictable and readable throughout the set, with no deviations in style or convention.
With 6 tools, the count is well-scoped for a Kibana MCP server focused on API exploration and execution. Each tool earns its place by covering distinct aspects like status, spaces, endpoint listing, searching, detailing, and execution, avoiding bloat while providing comprehensive functionality.
The tool set is highly complete for exploring and interacting with Kibana APIs, covering discovery (list/search), details, spaces, status, and execution. A minor gap exists in lacking direct CRUD operations for Kibana objects like dashboards or visualizations, but agents can work around this using execute_kb_api for custom requests.
MCP server for Product Management
MCP server for medicaid-intelligence
The official MCP Server from Mia-Platform to interact with Mia-Platform Console
