hunaras-mcp
MCP server for Hunaras, an AI-native recruiting platform that enables candidates and employers to manage jobs, applications, assessments, and talent sourcing through natural language.
README
hunaras-mcp
MCP server for Hunaras — an AI-native recruiting platform.
Connect any MCP-compatible AI assistant (Claude, ChatGPT, etc.) to Hunaras and manage your entire recruiting workflow through natural language.
What You Can Do
Candidates (17 tools):
- Search and apply for jobs
- Check AI interview assessments and scores
- Manage your profile and LinkedIn sync
- Respond to meeting proposals
- Rate employers
- Track notifications
Employers (6 tools):
- Post jobs and manage listings
- Search the talent pool (semantic search)
- Source candidates from LinkedIn
- View candidate profiles and AI assessments
Shared (1 tool):
- Get market insights (job counts, salary ranges, demand data)
Setup
1. Get an API key
Sign up at hunaras.com, then go to Settings > API Keys to create one.
2. Configure your MCP client
Claude Desktop / Claude Code
Add to your MCP config (claude_desktop_config.json or .mcp.json):
{
"mcpServers": {
"hunaras": {
"command": "npx",
"args": ["-y", "hunaras-mcp"],
"env": {
"HUNARAS_API_KEY": "hnar_your_api_key_here"
}
}
}
}
Other MCP clients
{
"command": "npx",
"args": ["-y", "hunaras-mcp"],
"env": {
"HUNARAS_API_KEY": "hnar_your_api_key_here"
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
HUNARAS_API_KEY |
Yes | — | Your API key (starts with hnar_) |
HUNARAS_API_URL |
No | https://hunaras.com |
API base URL (for self-hosted instances) |
Tools
Candidate Tools
| Tool | Description |
|---|---|
search_jobs |
Search jobs using AI semantic search |
get_job_details |
Get full job posting details |
apply_to_job |
Submit a job application |
get_my_profile |
View your candidate profile |
get_my_applications |
List applications with statuses |
update_profile |
Update profile fields |
update_visibility |
Show/hide from talent pool |
get_my_assessments |
List AI interview assessments |
get_assessment_details |
Full assessment report with scores |
get_my_appointments |
List meeting proposals |
respond_to_appointment |
Accept, reschedule, or reject meetings |
get_my_notifications |
List notifications |
mark_notifications_read |
Mark notifications as read |
get_my_ratings |
View ratings from employers |
rate_employer |
Rate an employer |
get_pending_ratings |
See which employers you can rate |
sync_linkedin |
Sync profile with LinkedIn |
Employer Tools
| Tool | Description |
|---|---|
create_job |
Post a new job listing |
list_my_jobs |
List your job postings |
search_candidates |
Semantic search across talent pool (Pro) |
get_candidate_profile |
View candidate profile + assessment (Pro) |
hunt_candidates |
Source candidates from LinkedIn (Pro) |
invite_candidate |
Invite external candidate to platform |
Shared Tools
| Tool | Description |
|---|---|
get_market_insights |
Job market data, salary ranges, demand |
Example Conversations
Find a job:
"Find me React developer jobs in Berlin" "Show me details for the first one" "Apply with a cover letter highlighting my 5 years of experience"
Check interview results:
"How did I do on my interviews?" "Show me the detailed assessment for the frontend role"
Employer hiring:
"Post a senior backend engineer role, remote, $150k-$180k" "Search for candidates with Python and AWS experience"
Pricing
- Candidates: Always free
- Employers Free: 2 active jobs, 1 candidate reveal
- Employers Pro ($200/mo): Unlimited jobs, reveals, talent pool search, scheduling
Links
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。