OpenGxP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
OpenGxP
Guideline-as-code MCP servers for the regulated half of drug development.
Everyone has built MCP servers that look things up (PubMed, ChEMBL, trials, FAERS). OpenGxP builds the tools pharma actually works under: deterministic, cited, tested implementations of ICH/FDA guidelines that any agent (Claude, GPT, open models) can call.
Decision support only. Verify against the current guideline and your site SOPs.
v0.1: cmc server
Tool | Guideline | What it answers |
| ICH Q3A(R2) / Q3B(R2) | Reporting / identification / qualification thresholds at a dose, and which impurities cross them (with the guideline's rounding rules) |
| ICH Q3C(R9) | Class, PDE, Option 1/2 limits, pass/fail, Option 2 sum across components |
| ICH Q3D(R2) | Elements to assess by route, PDEs, permitted concentrations, % of PDE, 30% control threshold, main contributing component, cutaneous CTCL |
Resources: ich://q3c/solvents, ich://q3c/solvents/{name|CAS|synonym}, ich://q3d/elements, ich://q3d/elements/{symbol}.
Prompt: impurity_assessment_report.
Every result carries: summary, findings (info / warning / action_required), assumptions,
citations (guideline + section + rule), provenance (tool and guideline version, sha256 of inputs,
the worked examples this code path is validated against) and a disclaimer.
Related MCP server: Biomedical APIs MCP Server
v0.2: stab server
Tool | Guideline | What it answers |
| ICH Q1E 2.6, Appendix B | ANCOVA batch poolability (slopes then intercepts, α = 0.25), most reduced model, earliest time the 95% confidence bound meets the criterion, shortest batch, capped by the Q1E extrapolation limits; flags curvature, outliers, thin data |
| ICH Q1E 2.4–2.5, Appendix A | How far beyond the long-term data (X) the shelf life (Y) may go, with the decision path |
| PhRMA OOT paper (2003) | Out-of-trend results by regression control chart, by time point, or slope control |
| ICH Q1A(R2), WHO zones | Long-term / intermediate / accelerated conditions, minimum months, 'significant change' definition |
Data go in as structured points or plain CSV (batch,time_months,value). Resources: ich://q1a/significant-change, who://climatic-zones. Prompt: shelf_life_justification.
v0.3: sdtm server (CDISC CORE)
Wraps the official open-source CDISC CORE CLI (MIT) instead of reimplementing it.
Tool | What it does |
| Is CORE installed, which version; setup steps if not |
| Runs CORE on SDTM / SEND / ADaM datasets (+ Define-XML, CT packages, rule subset); returns issues grouped by rule with counts, CDISC/FDA rule IDs and example records; stores the full report |
| Re-pages / re-filters a stored run (by domain, rule, dataset) without re-running CORE |
| What a CORE rule checks: message, IG references and sections, check logic |
| Fixed / new / unchanged issues per rule between two runs; |
Prompt sdtm_fix_loop runs the self-correcting conformance loop. Setup: pip install opengxp[cdisc] (only needed for a repo clone), download a CORE release, set OPENGXP_CORE to its core executable (or to core.py in a clone).
Validation
Tests are built from the guidelines' own worked examples and tables:
Q3A(R2) and Q3B(R2) Attachment 2 examples (rounding + threshold comparison), Attachment 1 band edges
Q3C(R9) Tables 1–4 and both acetonitrile Option 1/2 examples
Q3D(R2) Tables A.2.1, A.2.2, A.5.1 and the Appendix 4 Options 1 / 2a / 2b example
CORE adapter: CLI arguments, report parsing (CORE v1.0.0 JSON format), paging, filters, run diffs and rule explanations, tested against a stand-in CLI that writes that format
Q1E: ANCOVA p-values, slopes, residual SD and confidence bounds match statsmodels to 1e-9; analytic crossing times; every branch of the extrapolation rules
uv run pytestUse it
uv run opengxp # stdio MCP serverClaude Desktop / Claude Code config:
{ "mcpServers": { "opengxp": { "command": "uv", "args": ["--directory", "/path/to/opengxp", "run", "opengxp"] } } }Roadmap
ICH M7, DailyMed label diffs. See PLAN.md and DESIGN.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Chemistry, pharma and biotech tools for AI assistants: NMR, MS, IR and UV analysis, ADMET and ICH M7, stability (ICH Q1), HPLC methods, DoE, docking, retrosynthesis, biologics. Deterministic results you can check. Built in Leipzig, Germany.
Pharmacogenomics for AI agents: cited drug–gene, gene and rsID lookups plus a medication screen.
Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
15 deterministic validation tools for AI agents: tax IDs (15 countries), VAT, IBAN, LEI, HS codes.
Related MCP Servers
- AlicenseAqualityDmaintenanceExposes CDISC standards data including SDTM, ADaM, CDASH, and Controlled Terminology as tools for AI assistants via the CDISC Library API. It enables users to search standards, retrieve domain variables, and access codelist definitions to facilitate clinical research data management.12MIT
- FlicenseBqualityDmaintenanceEnables AI agents to query free biomedical and pharmaceutical APIs for clinical trials, drug data, molecular structures, adverse events, and research literature.14-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, risk-assess, request, and track actions on validated BioPharma systems (LIMS, MES, QMS, ELN) without bypassing the validated state, routing each request through GAMP 5 risk classification, ALCOA+ checks, approval workflows, and 21 CFR Part 11 e-signatures. Agents can also retrieve signed, verifiable execution records and audit evidence for the actions they perform.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables testing healthcare AI agents against cited FDA labels and coded answer keys by verifying medication order text and structured claims deterministically, with cited results, FDA reference lookups, and scored exams.9Apache 2.0