
Clinical Trial Design
If you're designing Phase 2 or Phase 3 trials, this gives Claude direct access to gsDesign, gsDesign2, and graphicalMCP through nine MCP tools. You get sample size calculations for binary, continuous, and time-to-event endpoints (both proportional hazards and non-proportional frameworks like MaxCombo and RMST), group sequential boundaries with configurable spending functions, and multiplicity adjustments including graphical procedures. The operational kernel solves accrual-duration-sample size relationships and flags feasibility violations. Monte Carlo verification cross-checks closed-form results, and the reporting tool exports to Word or PDF with citation chains. It's backed by 288 R tests and includes a benchmark corpus of 176 public trial designs for validation.
- tools
- 9
- transport
- STDIO
- env vars
- 2
- last updated
- Apr 29, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
design_binaryDesigns a trial with a binary event/no-event endpoint, fixed or group-sequential.
Designs a trial with a binary event/no-event endpoint, fixed or group-sequential.
No parameter schema in public metadata yet.
design_continuousDesigns a trial with a continuous mean-difference endpoint, fixed or group-sequential.
Designs a trial with a continuous mean-difference endpoint, fixed or group-sequential.
No parameter schema in public metadata yet.
design_survivalDesigns a time-to-event trial across PH and non-proportional hazards models, fixed or group-sequential.
Designs a time-to-event trial across PH and non-proportional hazards models, fixed or group-sequential.
No parameter schema in public metadata yet.
design_co_primaryDesigns trials with two or more co-primary endpoints using fixed-sequence, alpha-split, or Bonferroni strategies.
Designs trials with two or more co-primary endpoints using fixed-sequence, alpha-split, or Bonferroni strategies.
No parameter schema in public metadata yet.
design_multi_populationDesigns trials testing the same endpoint across multiple populations, with nested or disjoint relations.
Designs trials testing the same endpoint across multiple populations, with nested or disjoint relations.
No parameter schema in public metadata yet.
design_graphical_multiplicityDesigns multi-hypothesis trials with alpha recycling via a graphical (Maurer-Bretz) procedure.
Designs multi-hypothesis trials with alpha recycling via a graphical (Maurer-Bretz) procedure.
No parameter schema in public metadata yet.
validate_against_benchmarkReplays a benchmark case through its matching design tool and diffs against expected values within tolerance.
Replays a benchmark case through its matching design tool and diffs against expected values within tolerance.
No parameter schema in public metadata yet.
verify_designMonte Carlo cross-check of a design result under H0 and H1 with power and Type I error tolerance gates.
Monte Carlo cross-check of a design result under H0 and H1 with power and Type I error tolerance gates.
No parameter schema in public metadata yet.
design_reportRenders a clinician-readable design summary in markdown, Word, or PDF format.
Renders a clinician-readable design summary in markdown, Word, or PDF format.
No parameter schema in public metadata yet.
Sponsors
Configuration
DESIGNR_RSCRIPTOptional override for the Rscript binary path. Defaults to whatever 'Rscript' resolves to on the system PATH. Set this if R isn't on PATH or you need a specific R version.
DESIGNR_LAUNCHEROptional override for the R launcher path (the inst/launcher.R that sources the R sources and dispatches the JSON). Defaults to the bundled launcher. Set this only if you need to use a non-bundled R source tree.
Readme
clinical-trial-design
A Claude Code plugin and MCP server for end-to-end clinical trial design.
clinical-trial-design helps biostatisticians and clinical trialists design Phase 2 and Phase 3 confirmatory studies through a conversational interface, backed by validated R packages (gsDesign, gsDesign2, graphicalMCP).
v0.0.13 — pre-beta. Nine MCP tools across single-primary endpoint design (binary, continuous, time-to-event under PH and four NPH frameworks), multi-hypothesis design (co-primary, multi-population, graphical multiplicity / Maurer-Bretz), Monte-Carlo verification, and Word/PDF reporting. Reasoning-chain schema with sponsor-confidential redaction. Operational kernel solves accrual ↔ duration ↔ N, plus optional
max_n/max_durationfeasibility warnings. 288/288 R tests, 18/18 MCP smoke. Published to npm (clinical-trial-design) and the official MCP registry (io.github.wei-ai-lab/clinical-trial-design). Full change history in CHANGELOG.md; API contract in API_STABILITY.md.
What it is
clinical-trial-design has four layers:
Details
- Repository
- github.com/wei-ai-lab/clinical-trial-design
- Category
- Design & Creative
- Package
clinical-trial-design- Transport
- STDIO
- Registry
- MCP registry, active