@kula-ai/mcp-server

@kula-ai/mcp-server

MCP server enabling AI assistants to connect to Kula recruiting API for managing jobs, candidates, applications, webhooks, and more.

Category
访问服务器

README

@kula-ai/mcp-server

CI npm License: MIT Node

An MCP (Model Context Protocol) server for the Kula recruiting API. Connect AI assistants like Claude to your Kula account to list jobs, manage applications, configure webhooks, and more.

Quick Start

With Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "kula": {
      "command": "npx",
      "args": ["-y", "@kula-ai/mcp-server"],
      "env": {
        "KULA_API_KEY": "your_api_key_here"
      }
    }
  }
}

<details> <summary>With Cursor</summary>

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "kula": {
      "command": "npx",
      "args": ["-y", "@kula-ai/mcp-server"],
      "env": {
        "KULA_API_KEY": "your_api_key_here"
      }
    }
  }
}

</details>

<details> <summary>With Claude Code</summary>

claude mcp add kula -- npx -y @kula-ai/mcp-server

Then set KULA_API_KEY in your environment.

</details>

Manual

npx @kula-ai/mcp-server

Configuration

Environment Variable Required Description
KULA_API_KEY Yes Your Kula API key

Get your API key from Kula Developer Settings.

Available Tools

51 tools across 13 categories:

<details> <summary>Organization (4 tools)</summary>

Tool Description
list_departments List all departments in the organization as a nested tree structure
list_offices List all offices in the organization
list_milestones List all hiring milestones (pipeline stage groupings)
list_users List all active internal users (recruiters, hiring managers, coordinators)

</details>

<details> <summary>Sources (1 tool)</summary>

Tool Description
list_sources List all candidate sources in the organization

</details>

<details> <summary>Rejection Reasons (1 tool)</summary>

Tool Description
list_rejection_reasons List all rejection reasons configured in the organization

</details>

<details> <summary>Custom Fields (1 tool)</summary>

Tool Description
list_custom_fields List custom fields by subject type. Required — valid values: job, candidate, requisition, offer

</details>

<details> <summary>Jobs (3 tools)</summary>

Tool Description
list_jobs List jobs with filters (status, department, office, date ranges, sort)
search_jobs Search jobs by title (partial match) with optional filters
get_job Get details of a specific job

</details>

<details> <summary>Job Stages (3 tools)</summary>

Tool Description
list_job_stages List all pipeline stages for a specific job
create_job_stage Create a new pipeline stage for a job
list_stage_activities List all activities configured for a specific job stage

</details>

<details> <summary>Job Posts (2 tools)</summary>

Tool Description
list_job_posts List published job posts on the job board
get_job_post Get details of a specific job post from the job board

</details>

<details> <summary>Candidates (5 tools)</summary>

Tool Description
create_candidate Create a new candidate in the system
list_candidates List candidates with simple filters (email, date ranges, sort)
search_candidates Search candidates by name, email, skills, tags, location, and more
get_candidate Get details of a specific candidate
update_candidate Update an existing candidate's profile

</details>

<details> <summary>Applications (6 tools)</summary>

Tool Description
list_applications List job applications
get_application Get details of a specific application
update_application_stage Update the stage of a specific application
list_application_notes List notes on a specific application
create_application_note Add a note to a specific application
update_application_note Update an existing note on an application

</details>

<details> <summary>Scorecard Submissions (1 tool)</summary>

Tool Description
list_scorecard_submissions List scorecard submissions for a specific application

</details>

<details> <summary>Webhooks (12 tools)</summary>

Tool Description
list_webhooks List all configured webhooks
create_webhook Create a new webhook subscription
get_webhook Get details of a specific webhook
update_webhook Update an existing webhook configuration
delete_webhook Delete a webhook
enable_webhook Enable a disabled webhook
disable_webhook Disable an active webhook
rotate_webhook_secret Rotate the signing secret for a webhook
test_webhook Send a test payload to a webhook endpoint
list_webhook_logs List recent delivery logs for a webhook
list_webhook_events List all available webhook event types
get_webhook_sample_payload Get a sample webhook payload for a specific event type

</details>

<details> <summary>Requisitions (6 tools)</summary>

Tool Description
list_requisitions List all requisitions for your account
get_requisition Get detailed information about a specific requisition
list_requisition_fields List default and custom field definitions for requisitions
create_requisition Create a new requisition (supports linked groups via head_count)
update_requisition Update an existing requisition
close_requisition Close a requisition

</details>

<details> <summary>Autocomplete (6 tools)</summary>

Tool Description
search_companies Search companies by name
list_industries List all available industries
search_locations Search locations by query
search_institutions Search academic institutions by name
search_disciplines Search academic disciplines by name
list_degrees List all available academic degrees

</details>

Development

# Use correct Node version
nvm use

# Install dependencies
npm install

# Build
npm run build

# Watch mode
npm run dev

# Run tests
npm test

# Test with MCP Inspector
npx @modelcontextprotocol/inspector node build/index.js

Connecting locally

To test your local build with an AI client instead of the published package:

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "kula": {
      "command": "node",
      "args": ["/absolute/path/to/kula-mcp/build/index.js"],
      "env": {
        "KULA_API_KEY": "your_api_key_here"
      }
    }
  }
}

<details> <summary>With Cursor</summary>

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "kula": {
      "command": "node",
      "args": ["/absolute/path/to/kula-mcp/build/index.js"],
      "env": {
        "KULA_API_KEY": "your_api_key_here"
      }
    }
  }
}

</details>

<details> <summary>With Claude Code</summary>

claude mcp add kula -- node /absolute/path/to/kula-mcp/build/index.js

Then set KULA_API_KEY in your environment.

</details>

Note: The server uses STDIO transport, so there's no hot-reload. After rebuilding (npm run build or via npm run dev), restart the MCP client to pick up changes.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选