A side-by-side look at the Ollos MCP and Saliga data tools (Apify) MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Ollos MCP for speech-to-text work as a local process; choose Saliga data tools (Apify) for speech-to-text. You can also run both side by side in one mcpServers block.
ollos_probe, ollos_transcribe, ollos_keyframes.APIFY_TOKEN.Rows where the two servers differ are marked.
| Spec | S Saliga data tools (Apify) | |
|---|---|---|
| Category | Speech-to-Text | Speech-to-Text |
| Quality signal | 55/100 · Good | 36/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | None listed | APIFY_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 8 | Not listed |
| Full listing | View Ollos MCP | View Saliga data tools (Apify) |
ollos_probeWhat the file really is: kind, duration, resolution, aspect (and which platforms it fits), codecs, tracks. Detects Zoom recording folders. Instant.ollos_transcribeWhisper transcription with timestamps. Voice-activity gating skips silence; known hallucinations are filtered; `vocabulary` fixes domain terms.ollos_keyframesThe frames that carry information, packed into 3×3 timestamped contact sheets. Works on screen recordings where scene detection sees nothing.ollos_read_screenOCR of on-screen text plus a **secret scan**: API keys, JWTs, `.env` lines, private deployment URLs. Always masked.ollos_reviewVerdict before publishing: loudness vs platform, silences to cut, aspect ratio, secrets on screen.ollos_framesLook at a sheet or a single frame as an image.ollos_diarizeWho spoke when: pyannote segmentation + WeSpeaker embeddings + clustering, with an 8-second voice clip per speaker so you can name them by ear. Uses Zoom per-participant tracks directly when present. *Experimental — see limits.*ollos_searchHybrid BM25 + multilingual-embedding search over everything transcribed and read, fused by reciprocal rank. Returns passages with timestamps, never whole transcripts.No tool names declared yet. Check the project README from the listing page.
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"ollos-mcp": {
"command": "npx",
"args": [
"-y",
"ollos-mcp"
]
}
}
}
No confirmed install command for Saliga data tools (Apify) yet — follow the setup steps linked from its listing page rather than a guessed package name.