SenseCritiq MCP Server
mcp-name: io.github.salvisare/sensecritiq
SenseCritiq turns raw research into actionable insights - automatically.
Upload an interview recording, transcript, or survey and Claude will transcribe it, extract themes, surface verbatim quotes with speaker attribution, and generate structured findings in minutes. No more manual affinity mapping. No more hours spent tagging transcripts. Your entire research history becomes queryable in plain language.
Built for UX researchers, product teams, and anyone who talks to users.
What you can do
- Upload any format - audio (mp3, m4a, wav, mp4), transcripts (txt, pdf, docx)
- Get structured synthesis - themes, key findings, verbatim quotes - each pinned to speaker and timestamp
- Search across all sessions - semantic search over your full research history
- Generate reports - export as Markdown or PDF with one tool call
- Query in plain language - ask questions across months of research, get cited answers
Setup
- Sign up and get your API key at sensecritiq.com
- Add to your Claude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"sensecritiq": {
"command": "uvx",
"args": ["sensecritiq-mcp"],
"env": {
"SCQ_API_KEY": "scq_live_your_key_here"
}
}
}
}
- Restart Claude Desktop. SenseCritiq tools will appear automatically.
Tools
upload_research_file
Upload an audio recording, video, or transcript for processing. Returns a session_id to track progress.
Parameters: file_path (required), session_name (required), project_id (optional), tags (optional)
get_session_status
Poll processing status after upload. Values: queued → processing → ready → failed.
Parameters: session_id (required)
get_synthesis
Retrieve themes, key findings, and quote count for a completed session. Every finding cites a verbatim source.
Parameters: session_id (required)
get_quotes
Get verbatim quotes from a session, optionally filtered by theme. Each quote includes speaker label and timestamp.
Parameters: session_id (required), theme_id (optional)
search_research
Semantic search across your entire research history. Ask questions in plain language and get cited answers.
Parameters: query (required), project_id (optional), date_from (optional), date_to (optional)
list_sessions
List all research sessions, optionally filtered by project.
Parameters: project_id (optional), limit (default 20), offset (default 0)
generate_report
Generate a formatted report for a session. Returns a pre-signed download URL valid for 24 hours.
Parameters: session_id (required), format (markdown | pdf | notion)
Example usage in Claude
Upload session-04.m4a as "Onboarding exit interviews - March"
What do users say about the invite flow across all sessions?
Generate a PDF report for session sess_abc123
Supported file formats
| Type | Formats |
|---|---|
| Audio | mp3, m4a, wav, mp4 |
| Transcript | txt, pdf, docx |
Plans
| Plan | Sessions/month | Price |
|---|---|---|
| Free | 2 | $0 |
| Starter | 10 | $29/mo |
| Growth | 30 | $79/mo |
| Team | 150 | $199/mo |
All plans include full MCP server access and all 7 tools.
License
MIT
Metadata
Release files for sensecritiq-mcp 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| sensecritiq_mcp-0.1.5.tar.gz | 5.9 kB | Without provenance | Details for sensecritiq_mcp-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sensecritiq_mcp-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for sensecritiq_mcp-0.1.5-py3-none-any.whl |
Total release size: 17.4 kB
Release files / sensecritiq_mcp-0.1.5.tar.gz
| Download URL | sensecritiq_mcp-0.1.5.tar.gz |
|---|---|
| Size | 5.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d4791411325ab1214df6c8618f3b0428d35b4e72d8acd75a79c497427ccbc21d
|
|
BLAKE2b-256 checksum How to use checksums |
c0022027dbf25e66223b2cf48632d7e53278f3c95411f0f07509df19b6f309f1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / sensecritiq_mcp-0.1.5-py3-none-any.whl
| Download URL | sensecritiq_mcp-0.1.5-py3-none-any.whl |
|---|---|
| Size | 11.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f912072e2bf4b9513384f5e3447f8c3852755424cac3e9628e2080e19954c323
|
|
BLAKE2b-256 checksum How to use checksums |
b1420d9571fdacf45e36f60a16f5de4256723fa5ce3128e3e666dfaa5e3ccfd7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for sensecritiq-mcp 0.1.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.