boss-agent-cli
Related Servers
Alternatives to boss-agent-cli
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceMCP server for searching BOSS直聘 (Boss Zhipin) job listings. It provides a boss_search tool that supports multi-city queries, keyword filtering, and JSON output for AI agents.14MIT
- AlicenseNot gradedqualityBmaintenanceProvides MCP tools for job discovery, welfare filtering, resume and AI-assisted applications, and recruiter workflows across Chinese job platforms such as BOSS Zhipin, Zhilian, and 51job.MIT
- FlicenseNot gradedqualityCmaintenanceAutomates job searching and initial communication on the Boss Zhipin platform by parsing resumes and matching them with relevant job listings. It includes anti-bot detection features and supports automated messaging to HR representatives through various MCP clients.10-
- FlicenseNot gradedqualityAmaintenanceAutomates the recruiter-side hiring pipeline on the BOSS Zhipin platform, enabling batch multi-keyword candidate search, resume screenshot capture, filtering and scoring, share-link extraction, greetings, and Markdown report export through a logged-in local Chrome session. Exposes these actions as MCP tools that AI assistants such as Claude Code or Claude Desktop can drive end-to-end from natural-language requests.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to drive a logged-in BOSS Zhipin recruiter account through the Model Context Protocol, running multi-keyword candidate searches, capturing Canvas-rendered resume screenshots, extracting permanent share links, auto-filtering and scoring candidates, sending greetings, and exporting Markdown reports. Results persist in a local database so interrupted pipelines can resume without losing data.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants such as Claude to automate recruiter workflows on the BOSS Zhipin hiring platform, including multi-keyword candidate searches, resume screenshot capture for OCR, deduplication, filtering and scoring, Markdown report export, and one-click greeting outreach. It drives an already-logged-in Chrome browser over the DevTools Protocol and persists results to a local JSON database so interrupted pipelines can be resumed.-
TDQS
Scored across 78 tools
Multiple tool pairs are near-duplicates with unclear boundaries: boss_ai_optimize vs boss_ai_resume_optimize vs boss_ai_suggest (all resume improvement suggestions), boss_ai_analyze_jd vs boss_ai_fit (both matching analysis), boss_show vs boss_detail (both job detail), boss_hr_chat vs boss_chat, boss_hr_chatmsg vs boss_chatmsg. The five boss_agent_* "compatibility" tools coexist with boss_agent_run/train/date, so agents must guess which generation of the queue/pending/review API to use. Role prefixes (hr_ vs none) help somewhat, but description alone cannot reliably disambiguate many actions.
Names are uniformly snake_case and follow a boss_<domain>_<verb/object> namespace (hr_, ai_, agent_, crawl_, watch_, preset_, shortlist_), which is largely predictable. However, conventions drift within that namespace: some tools are verb-first (boss_search, boss_greet), some are noun-first (boss_chatmsg, boss_hr_candidates), compound words appear fused (chatmsg vs chat_summary, ai_reply vs ai_chat_coach), and duplicate concepts get different stems (optimize vs resume_optimize).
78 tools for a single job-board client is far beyond what an agent can navigate reliably; many are deprecated compatibility shims (boss_agent_pending, boss_agent_review, boss_agent_review_approve/reject) or thin variants of shorthands. The core workflows (search, detail, greet, chat, shortlist, apply) would fit in ~25 tools; the rest is layering and legacy bloat.
Coverage is broad and lifecycle-aware on both sides: candidate search/recommend/detail/greet/apply/chat/interview plus local shortlist, presets, watch, crawl, export, digest and stats, and recruiter-side jobs/candidates/greet/resume exchange/download/reply. Gaps are minor: no tool to edit or delete a stored resume, and the AI optimization tools only emit drafts rather than writing back, but core workflows have no dead ends.