Hosted MCP server for the oruk Speech API: transcription + speech emotion/tone a
Hosted MCP server for the oruk Speech API: transcription + speech emotion/tone analysis for coding agents. No local install.
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://oruk.ai/mcp |
|---|---|
| Source | https://github.com/Oruk-AI/oruk-mcp |
| Transport | http |
| Tools | 8 |
| Auth | none |
| First seen | 2026-09-06 23:21:45 |
| Last checked | 2026-11-17 21:47:37 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 451 / 1886 ms |
| Last successful check | 2026-11-17 21:47:37 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (8)
oruk_plan_hume_migration— Return bounded planning guidance from redacted enums and counts only. No key is needed. Never send source, paths, audio, credentials or provoruk_analyze_speech— Transcribe English audio AND score how it was said in one call: transcript, tagged transcript, selected scores from 15 emotion and 16 speakioruk_transcribe_audio— Transcribe prerecorded English audio to text with time-ordered segments and word timings. Use this when only the words matter. Accepts wav/foruk_analyze_tone— Score how speech sounds without transcribing it: selected emotion (happy, frustrated, worried, …) and speaking-style (sarcastic, confident,oruk_check_usage— Verify that an Oruk API key works and report the subscription, remaining audio minutes, and recent API usage. Use this after setup or to diaoruk_create_trial_key— Mint a real, temporary oruk API key with no account required: 3 requests, expires in 30 minutes, spends from a capped shared budget. Use thioruk_list_models— List oruk’s speech models with lifecycle, current subscription plans, and explicitly labeled legacy reference rates, the five API tasks, theoruk_get_started— Quickstart for the oruk Speech API and this MCP server: how to get an API key, per-client MCP configuration snippets, SDK install commands,
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:47:37 | ✓ | ✓ | 1711 ms | 87 | active |
| 2026-11-17 21:32:31 | ✓ | ✓ | 477 ms | 90 | active |
| 2026-11-17 21:17:20 | ✓ | ✓ | 183 ms | 94 | active |
| 2026-11-17 21:02:19 | ✓ | ✓ | 297 ms | 93 | active |
| 2026-11-17 20:47:00 | ✓ | ✓ | 242 ms | 93 | active |
| 2026-11-17 20:31:59 | ✓ | ✓ | 253 ms | 93 | active |
| 2026-11-17 20:16:52 | ✓ | ✓ | 258 ms | 93 | active |
| 2026-11-17 20:01:13 | ✓ | ✓ | 1546 ms | 86 | active |
| 2026-11-17 19:45:58 | ✓ | ✓ | 391 ms | 90 | active |
| 2026-11-17 19:30:50 | ✓ | ✓ | 239 ms | 93 | active |
| 2026-11-17 19:15:49 | ✓ | ✓ | 2036 ms | 86 | active |
| 2026-11-17 18:59:54 | ✓ | ✓ | 283 ms | 93 | active |
| 2026-11-17 18:44:53 | ✓ | ✓ | 296 ms | 93 | active |
| 2026-11-17 18:29:52 | ✓ | ✓ | 346 ms | 90 | active |
| 2026-11-17 18:14:47 | ✓ | ✓ | 494 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://oruk.ai/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/oruk-ai-mcp # JSON