TrialWatch
cognis-digital/trialwatch
Monitor de ensaios clínicos com diffs e alertas, CI-ready, self-hostable
Ver no GitHubMCP server para consultar, comparar e monitorar registros de ensaios clínicos no ClinicalTrials.gov, gerando alertas automatizados sobre mudanças de status, recrutamento ou resultados. Integra-se nativamente com agentes Claude via protocolo MCP e oferece saídas estruturadas em JSON, tabelas ou SARIF para CI/CD.
Instalação
npx convez-ai cognis-digital/trialwatch1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Rastrear mudanças de status em ensaios clínicos específicos para investimento ou pesquisa
- Automatizar verificações periódicas de elegibilidade e recrutamento de pacientes
- Integrar monitoramento de dados clínicos em pipelines de CI/CD com gates de qualidade
Veredito

Ferramenta especializada e bem-arquitetada para o nicho de life sciences e biotech, com MCP-first design que potencializa agentes Claude. Viável para pesquisadores, analistas de investimento e plataformas de advocacy de pacientes que precisam monitorar ClinicalTrials.gov programaticamente.
README
A tradução para o português deste README ainda está na fila.
TRIALWATCH
Query, diff, and monitor ClinicalTrials.gov records, alerting on status, enrollment, or result changes.
Healthcare & Life-Sciences — HIPAA, PHI, FHIR/HL7, and clinical data.
pip install cognis-trialwatch
trialwatch scan . # → prioritized findings in seconds
Contents
- Why trialwatch? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why trialwatch?
Biotech analysts and patients get a CI-schedulable 'is my trial still recruiting?' tracker with clean JSON diffs — built-in catnip for the investing/patient-advocacy crowd.
trialwatch is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.
Features
- ✅ Normalize Trial
- ✅ Load Trials From Obj
- ✅ Load Trials
- ✅ Diff Trials
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-trialwatch
trialwatch --version
trialwatch scan . # scan current project
trialwatch scan . --format json # machine-readable
trialwatch scan . --fail-on high # CI gate (non-zero exit)
Example
$ trialwatch scan .
[HIGH ] TRI-001 example finding (./src/app.py)
[MEDIUM ] TRI-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
Architecture
flowchart LR
A[Input: file / dir / API] --> B[Collectors]
B --> C[Rules / Analyzers]
C --> D[Scorer]
D --> E{Reporters}
E --> F[Table]
E --> G[JSON / SARIF]
E --> H[MCP tool -. drives .-> AI agents]
Use it from any AI stack
trialwatch is interoperable with every popular way of using AI:
- MCP server —
trialwatch mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
trialwatch scan . --format jsoninto any agent or LLM - LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
- CI / scripts — exit codes + SARIF for non-AI pipelines
How it compares
| Cognis trialwatch | ClinicalTrials.gov API + watchman | |
|---|---|---|
| Self-hostable, no account | ✅ | varies |
| Single command, zero config | ✅ | ⚠️ |
| JSON + SARIF for CI | ✅ | varies |
| MCP-native (AI agents) | ✅ | ❌ |
| Polyglot ports (JS/Go/Rust) | ✅ | ❌ |
| Open license | ✅ COCL | varies |
Built in the spirit of ClinicalTrials.gov API + watchman, re-framed the Cognis way. Missing a credit? Open a PR.
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (trialwatch mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
Install — every way, every platform
pip install "git+https://github.com/cognis-digital/trialwatch.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/trialwatch.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/trialwatch.git" # uv
pip install cognis-trialwatch # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/trialwatch:latest --help # Docker
brew install cognis-digital/tap/trialwatch # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/trialwatch/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/trialwatch | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
phiscrub— Stream-scan logs, CSVs, and free-text notes for PHI (names, MRNs, SSNs, dates, addresses) and redact or tokenize in place.dicomsweep— De-identify DICOM imaging studies per the DICOM PS3.15 Annex E profile, scrubbing tags and burned-in pixel text.fhirlint— Validate FHIR R4/R5 resources and bundles against profiles (US Core, etc.) with precise, line-level error reporting.hl7tap— Parse, pretty-print, diff, and replay HL7 v2 messages over MLLP from the terminal.consentledger— Maintain a tamper-evident, hash-chained audit log of patient-data access and consent events.synthcohort— Generate statistically realistic synthetic patient cohorts (FHIR/CSV) from a schema spec for dev and testing.
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes
Contributing
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
⭐ If
trialwatchsaved you time, star it — it genuinely helps others find it.
License
Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.