A side-by-side look at the Conversion Tools and Ollos MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Conversion Tools for speech-to-text work; choose Ollos MCP for speech-to-text as a local process. You can also run both side by side in one mcpServers block.
ollos_probe, ollos_transcribe, ollos_keyframes.Rows where the two servers differ are marked.
| Spec | C Conversion Tools | |
|---|---|---|
| Category | Speech-to-Text | Speech-to-Text |
| Quality signal | 37/100 · Fair | 55/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | — | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | Not listed | 8 |
| Full listing | View Conversion Tools | View Ollos MCP |
No tool names declared yet. Check the project README from the listing page.
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.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.
No confirmed install command for Conversion Tools yet — follow the setup steps linked from its listing page rather than a guessed package name.
{
"mcpServers": {
"ollos-mcp": {
"command": "npx",
"args": [
"-y",
"ollos-mcp"
]
}
}
}