MCP server exposing Taiwan listed-company salary disclosures to an LLM under exp
MCP server exposing Taiwan listed-company salary disclosures to an LLM under explicit constraints, with a Claude Agent SDK researcher
active Production-safe Score 83/100 http no auth
At a glance
| Endpoint | https://salary-mcp-beige.vercel.app/mcp |
|---|---|
| Source | https://github.com/yschang1688/tw-salary-mcp |
| Transport | http |
| Tools | 7 |
| Auth | none |
| First seen | 2026-08-19 01:04:27 |
| Last checked | 2026-11-17 21:50:11 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 1814 / 2213 ms |
| Last successful check | 2026-11-17 21:50:11 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (7)
lookup_company— Look up one company's salary disclosure by TWSE/TPEx stock code or name. Use this when the question names a specific Taiwanese listed companindustry_stats— Summarise the pay distribution within one industry. Use this whenever you need to judge whether a company's pay is high or low for its sectotop_by_median— Rank companies by non-managerial median pay, highest first, with optional industry and floor filters. Use this for 'which companies pay thecompany_trend— Show one company's median pay for every year on record (2019-2025). Use this when the question is about direction over time — whether pay isanalyze_jd— Deterministic JD breakdown: which skill groups a job description asks for, each with its demand share in a fixed 1,086-posting corpus of Taiskill_gaps— Deterministic gap report: compare a job description against the skills the caller supplies, and say which of the JD's asks are covered, whicmarket_demand— Rank skill groups by how many corpus postings ask for them, optionally filtered by a name fragment; also reports the years-of-experience dis
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:50:11 | ✓ | ✓ | 1728 ms | 85 | active |
| 2026-11-17 21:19:35 | ✓ | ✓ | 1736 ms | 85 | active |
| 2026-11-17 20:41:28 | ✓ | ✓ | 1700 ms | 85 | active |
| 2026-11-17 19:56:36 | ✓ | ✓ | 2335 ms | 85 | active |
| 2026-11-17 19:26:47 | ✓ | ✓ | 2034 ms | 85 | active |
| 2026-11-17 18:47:23 | ✓ | ✓ | 1761 ms | 85 | active |
| 2026-11-17 18:17:20 | ✓ | ✓ | 1727 ms | 85 | active |
| 2026-11-17 17:41:25 | ✓ | ✓ | 1848 ms | 85 | active |
| 2026-11-17 16:56:30 | ✓ | ✓ | 1869 ms | 85 | active |
| 2026-11-17 16:26:16 | ✓ | ✓ | 1907 ms | 85 | active |
| 2026-11-17 15:39:56 | ✓ | ✓ | 1813 ms | 85 | active |
| 2026-11-17 14:41:24 | ✓ | ✓ | 1992 ms | 85 | active |
| 2026-11-17 13:57:44 | ✓ | ✓ | 1664 ms | 85 | active |
| 2026-11-17 13:26:24 | ✓ | ✓ | 1804 ms | 85 | active |
| 2026-11-17 12:55:09 | ✓ | ✓ | 1804 ms | 85 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://salary-mcp-beige.vercel.app/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/salary-mcp-beige-vercel-app-mcp # JSON