CHANGELOG.md

Changelog

0.8.22 — 2026-04-30

New features

• Extended WHO Prequalification drug coverage to include active pharmaceutical ingredients (APIs) alongside finished pharmaceutical products; search drug --region who --product-type api filters explicit WHO searches to API rows. (232)
• Added the CDC CVX/MVX vaccine identity bridge for default and EU/all vaccine-brand drug search, backed by local CDC bundle downloads and explicit refresh via biomcp cvx sync. (233)
• Added CDC WONDER VAERS as the aggregate vaccine adverse-event source for search adverse-event --source <faers|vaers|all>, including combined vaccine search, health visibility, and source inventory/docs surfaces. (235)
• Added the local GTR-backed diagnostic entity with search/get diagnostic, first-use bundle refresh, explicit biomcp gtr sync, and the supporting health/docs/spec contract. (236)
• Expanded diagnostic into a local multi-source surface with WHO Prequalified IVD infectious-disease products, source-aware search/get behavior, and explicit biomcp who-ivd sync. (237)
• Added FDA 510(k) and PMA regulatory overlays to get diagnostic <id> regulatory, rendering source-aware FDA device status when records match and a truthful empty regulatory section when they do not. (238)
• Added opt-in diagnostic pivots to gene and disease cards with get gene <symbol> diagnostics and get disease <name_or_id> diagnostics, backed by local GTR and WHO IVD diagnostic search. (239)
• Extended article search follow-up guidance with cross-entity keyword hints: JSON _meta.next_commands now includes gene and drug pivots for recognizable keyword patterns, while markdown See also: adds discover and get disease recovery paths for short disease-like phrases. (242)
• Added opt-in clinical_features disease output backed by MedlinePlus clinical summaries, reviewed HPO phenotype mapping, source-native evidence URLs, and unsupported-disease empty states via get disease <name> clinical_features. (252, 253, 254)
• Added offline routing via biomcp suggest <question> so worked-example prompts can resolve to structured _meta.workflow guidance without requiring a live tool call. (279)
• Added workflow-ladder sidecars and schema-backed _meta.ladder[] payloads so routed workflows can carry explicit ladder steps across the CLI/MCP contract. (282)
• Added richer CLI help examples for batch/variant-limit usage and preserved the parser-level skill uninstall contract through current help and MCP guard surfaces. (217, 224)
• Added opt-in article fulltext source-boundary coverage and PDF fallback so article retrieval can truthfully report source limits while recovering PDF text when structured fulltext is unavailable. (255, 256)
• Added DDInter-backed drug-drug interaction workflows with biomcp drug interactions <name>, get drug <name> interactions, local bundle health, source-scoped empty wording, and biomcp ddinter sync. (303)

Docs

• Added BioASQ-oriented how-to routing rows to skills/SKILL.md for gene-disease association, gene localization/protein-function, drug regulatory date, and variant clinical-significance workflows, steering agents to structured-data shortcuts before article search. (240)
• Refreshed architecture, source-integration, and current-state docs so the shipped architecture and CLI guidance match the post-decomposition repo surface. (272, 273, 274, 275)
• Repaired backtick quoting in the mustmatch study/spec contract, published BioASQ benchmark guidance, and made the canonical SKILL.md render/install contract explicit for agents and operators. (276, 280, 281)
• Aligned the public landing-copy contract with the shipped suggest and workflow landing bullets so make test-contracts accepts the current README and docs homepage feature counts. (286)
• Refreshed source, licensing, versioning, CLI decomposition, diagnostic, clinical-features, API-key, quality-bar, and staging-demo docs to match the shipped v0.8.22 surface and current local-runtime key expectations. (222, 272, 292, 304, 306, 314, 318, 329, 332, 341, 358, 362)

Fixes

• Changed custom CLI validation failures (BioMcpError::InvalidArgument) to exit 2, matching clap parser failures and separating bad usage from runtime failures. (353)
• Fixed suggest so resistance-to-drug mechanism questions anchor starter commands on the drug instead of filler text. (291)
• Patched rustls-webpki to the safe release line and made make check enforce the cargo-deny advisory gate alongside the existing license gate. (290)
• Fixed cargo-install compatibility, deterministic EMA freshness checks, OLS4 smoke routing, WHO drug JSON envelopes, and WHO API cache-limit wording so install, health, and explicit WHO/API drug searches stay stable. (218, 220, 226, 232)
• Added compact diagnostic rows and capped disease diagnostic pivots so gene/disease diagnostic follow-ups stay scannable and bounded. (266, 267)
• Replaced the stale GTR sample with a live-valid GTR example and added zero-result recovery for the local diagnostic surface. (268, 269)
• Tightened entity-aware article follow-ups with a same-session loop-breaker for overlapping suggestions and PubMed ESearch cleanup for bounded question-format filler words. (277, 278, 283)
• Improved sparse drug research-code recovery, relational discover filtering, trial help example/flag consistency, and CTGov intervention alias preservation so generated follow-up commands stay useful and shell-safe for degraded or ambiguous inputs. (302, 310, 313, 338, 339, 340, 342, 351, 357)
• Repaired the targeted SPEC_SMOKE_ARGS lane so it stores stable smoke section IDs and resolves them to current mustmatch pytest item IDs at runtime; the quality ratchet now checks collectability before stale line-qualified selectors can reach make spec-smoke. (288)
• Hardened update and machine-readable CLI contracts: biomcp update fails closed when checksum sidecars are missing, biomcp --json version documents its plain-text exception, biomcp --json list remains parseable, and short-literal update ratchets were replaced with structural behavior checks. (331, 333, 352, 355)
• Stabilized MCP stdio no-input guidance, cBioPortal study download idle/stall handling, disease clinical-feature specs, OLS4 disease/discover fallback IDs, WikiPathways parallel tests, and protein ComplexPortal specs with regression coverage. (326, 336, 345, 346, 350, 354, 358)
• Surfaced Semantic Scholar authentication/degradation status in article search and honored Retry-After during authenticated retries so throttled searches disclose source health and back off correctly. (364, 365, 366)

Internal

• Completed release/docs contract cleanup for the 0.8.22 line so the latest release notes, ticket inventory, and release metadata stay aligned. (264, 265)
• Made make check include the public Python/docs contract lane and added make release-gate as the named local release-blocking command, so release-readiness docs and validation profiles share one contract. (287)
• Reworked SPEC_SMOKE_ARGS handling around stable smoke inventory and current mustmatch pytest item IDs, and cleaned up .march artifact handling for repo submission paths. (270, 271)
• Migrated the release gate to the spec-v2 corpus, made spec-pr self-contained for March kickoff, restored release-gate reliability, and kept stable smoke, canary, cache-warm, and test-contract lanes aligned with the current shipped docs/spec surface. (294, 297, 298, 299, 300, 301, 307, 308, 344)
• Decomposed oversized CLI modules, absorbed residual line-cap allowlists, clarified the benchmark harness as internal, and added runtime-wiring/line-cap ratchets so structural cleanup cannot reintroduce public-surface drift. (309, 319, 320, 321, 322, 323, 324, 325, 334, 335, 343, 347)
• Strengthened release readiness with gene-all warm-budget coverage, local gate uv-build fixes, leaked-artifact cleanup, binary asset attributes, CI wrapper stale-binary warnings, Python 3.12/Rust 1.95 CI compatibility, self-contained local-data spec fixtures, and final v0.8.22 readiness audits before publish. (247, 258, 262, 263, 285, 289, 315, 316, 317, 327, 328, 330, 348, 363, 367)
• Recorded the diagnostic-entity, HPO clinical-feature, Obsidian vault, biomedical news, post-v0.8.21 shipped-surface, and neural-reranking reviews as architecture or deferred work unless runtime wiring shipped in the bullets above. (230, 243, 244, 245, 246, 284)

0.8.21 — 2026-04-16

New features

• Added article date-range filtering (--date-from/--date-to and --year-min/--year-max aliases) to search article. (182)
• Added EMA regulatory region (--region eu) to search drug and get drug, backed by local EMA human-medicine feeds; data auto-downloads on first use via biomcp ema sync. (203)
• Added entity-aware HATEOAS suggestions (_meta.next_commands) to article search JSON output; gene-anchored and keyword searches return contextually appropriate follow-up commands. (195, 202)
• Added article search fallback suggestions when discover resolves no entities, so dead-end queries get recovery paths. (204)
• Surfaced EuropePMC and PubMed first_index_date per article in search article --json; null for sources that do not expose index dates. (196)
• Expanded trial search with drug alias union so searches match trials registered under any approved drug name variant. (198)
• Surfaced opt-in section hints (More: block) in gene and disease base card responses; get gene <symbol> and get disease <name> now show funding and survival opt-in hints. (209)

Fixes

• Fixed search all --counts-only --json so sections correctly omit results, links, and total fields per the counts-only contract. (206)
• Disambiguated FAERS 404 (drug not in post-marketing database) from "found but no matching events"; added ClinicalTrials.gov fallback for adverse-event lookups when FAERS returns 404. (197)
• Improved error messages for study download 403/404 (actionable, with --list recovery hint) and DisGeNET 403 (env var name and docs URL). (212)
• Added study subcommand help descriptions and a regression test so help completeness is enforced going forward. (210)

Docs

• Refreshed architecture docs to the post-decomposition state: source map, modes prose, and MCP allowlist contract. (213)
• Fixed documentation drift: README source count, CHANGELOG WHO entry, and root help command count. (211)
• Published two blog posts on biomcp.org: daraxonrasib six-commands workflow article and a follow-up that removes biomcp-python references. (200, 201)

Internal

• Added mustmatch lint for spec bash blocks so spec sections that silently skip due to a missing pipe are now caught. (221)
• Untracked .march build artifacts from git so worktree state stays clean. (193)
• Added Compact Approval Fields spec block for EMA and EU regulatory data contract assertions. (194)
• Consolidated EnvVarGuard and TempDirGuard into a central test_support module shared across all test crates. (199)
• Added docs-only validation profile so make docs can run without triggering the full build gate. (205)
• Updated tar and rustls-webpki for active RustSec advisories. (207)
• Fixed 7 make test-contracts failures from assertion drift after the decomposition batch. (208)

0.8.20 — 2026-03-30

Security

• Security fix: remove partial API key from health output so shared operator reports no longer leak credential fragments. (067)
• Hardened the MCP allowlist so mutating study download paths stay blocked while the safe --list path remains available. (068)

Fixes

• Fixed batch --json so responses always include the _meta contract field. (069)
• Hardened the GWAS variant section against live decode failures. (070)
• Fixed gene-to-PGx and disease-to-drug See-also routing so those pivots land on the correct entity helpers. (077)
• Fixed large PMC OA full-text downloads that were timing out on bigger payloads. (080)

New features

• Added cross-entity See-also links for drug→PGx, gene→PGx, disease→study, and zero-result→discover routing. (076)
• Added the quality ratchet to make check so the repo gate now audits mustmatch lint, MCP allowlist coverage, and source-registry drift. (075)
• Added the study top-mutated helper plus disease literature fallback for missing direct evidence paths.
• Added SEER Explorer-backed disease survival sections so get disease <name_or_id> survival can show 5-year relative survival by sex for mapped cancers. (173)
• Added NIH Reporter funding sections so get gene <symbol> funding and get disease <name_or_id> funding can show top grants from the most recent 5 NIH fiscal years. (174)
• Added WHO Prequalification as the shipped local-data drug source for get drug <name> regulatory --region who and search drug --region who; run who sync to force-refresh the local CSV before freshness-sensitive regional drug lookups.

Improvements

• Reworked CLI help, typed-path guidance, and the skill catalog for self-teaching agent navigation. (072, 073, 074)
• get disease now shows full disease definitions instead of truncated characterizations. (080)
• get disease now separates defining phenotypic features from the full HPO list with ranked key-feature summaries. (081)
• get gene now shows UniProt protein isoforms in the protein section. (082)
• get drug now shows drug target family names alongside individual targets. (083)
• get gene now shows protein legacy names alongside current symbols. (084)
• get variant now shows variant legacy nomenclature alongside current HGVS names. (085)
• Improved purine-analog mechanism labels so ATC-exact and mechanism-of-action coverage stay aligned. (086)
• Closed the remaining BioASQ product gaps around protein function truncation, variant-specific targets, and disease feature coverage. (087)
• Replaced the in-shell mustmatch shim with the packaged mustmatch lint entrypoint plus a small compatibility layer for the repo’s existing ratchet contract. (088)

Docs

• Added architecture contract docs for See-also links, discover grammar, CI, and post-tag public proof expectations. (078)
• Documentation consistency audit across the public docs surface.
• Repo cleanup for layout, example paths, and tracked .march artifacts. (079)

0.8.19 — 2026-03-26

Improvements

• Cleaned up Semantic Scholar health output so unauthenticated setups are reported as optional/shared-pool usage instead of looking like a broken configuration. (055)
• Added six more built-in study chart types: pie, density, violin, ridgeline, heatmap, and stacked bar. (041)
• EMA-backed drug data now auto-downloads on first use and refreshes stale local caches, so EU drug coverage no longer requires manual setup. (057)

CI

• Moved EMA-backed specs out of the PR-blocking stable lane into the smoke lane so CI keeps EMA coverage without destabilizing the release gate. (056)

Docs

• Refreshed the README, docs index, and source landing pages with clearer public-facing messaging.
• Added three new blog posts covering agent skills, article search, and built-in cancer genomics charts.

0.8.18 — 2026-03-25

New sources

• Added EMA regional drug coverage backed by local EMA human-medicine feeds, so search drug, get drug, and get drug shortage support --region us|eu|all across EU regulatory status, DHPCs, referrals, PSUSAs, shortages, and the existing US label surface. (043, 044)
• Added the BioASQ benchmark module with benchmarks/bioasq/ingest_public.py, dataset and validity manifests, and the published BioASQ benchmark reference at docs/reference/bioasq-benchmark.md. (045, 046)

Improvements

• search drug now defaults to --region all, get drug --region is surfaced in help, OpenFDA label fallback prefers exact brand-name matches, and OpenTargets drug-indication lookups are corrected for mixed US/EU workflows. (043, 044)
• S2_API_KEY is now optional for Semantic Scholar-backed article enrichment and helpers: unauthenticated calls use the shared Semantic Scholar pool at 1 req/2sec, while authenticated calls keep the 1 req/sec quota with retry backoff. (047)

0.8.17 — 2026-03-23

New sources

• Added WikiPathways as a third pathway source alongside Reactome and KEGG, with source-aware section handling plus operator proof coverage in biomcp health and scripts/contract-smoke.sh. (025)
• Added an optional Semantic Scholar search leg to search article when S2_API_KEY is set, merging PubTator3, Europe PMC, and Semantic Scholar results with identifier-aware deduplication and directness-first ranking. (034)
• Added KEGG as a pathway source alongside Reactome and WikiPathways.
• Added gnomAD constraint metrics for variant-interpretation context.
• Added Human Protein Atlas tissue expression to gene output.
• Added ComplexPortal-backed protein complex data.
• Added DisGeNET gene-disease association scores.

New commands

• Added biomcp discover <query> as the free-text concept-resolution entrypoint, using OLS4 as the required backbone with optional UMLS crosswalks and MedlinePlus disease/symptom context. (028)
• Added biomcp article batch <id>... for compact multi-article summary cards with parallel article fetch and optional batched Semantic Scholar enrichment; the command is limited to 20 IDs. (037)

Improvements

• Restored pathway progressive disclosure and exact-title-first ranking, so default pathway cards stay concise and exact pathway-title matches rise to the top across sources. (017)
• Expanded operator proof surfaces and refreshed source-aware architecture docs so the shipped source inventory, API-key handling, proof expectations, and section-availability rules are explicit and consistent. (018, 019, 030)
• Improved protein complexes terminal layout and normalized pathway CLI usage errors and remediation. (020, 021)
• Added source labels and missing evidence URLs across entity detail outputs in Markdown and JSON for stronger traceability. (022, 025)
• Added paper/reproducibility and community-packaging artifacts, including paper/, CONTRIBUTING.md, CODE_OF_CONDUCT.md, and .zenodo.json. (023)
• get gene and get drug misses now return discovery-backed canonical suggestions with structured _meta.alias_resolution / _meta.next_commands guidance instead of dead-end errors. (029)
• Help, list, and docs now surface working typed paths, and search all / search article can emit --debug-plan routing metadata in Markdown or JSON when requested. (032)
• Typed variant retrieval now accepts common shorthand forms, emits variant-scoped recovery guidance on misses, and accepts long-form protein notation such as AKT2 p.Pro50Thr. (033, 039)
• search all cross-routing now stays inside controlled typed fallback rules, reducing noisy drill-downs and duplicate follow-up commands. (035)
• Typed retrievals now expose compact answer-bearing summaries for approvals, population frequencies, and disease/variant evidence without removing the detailed sections. (036)
• Deepened OpenTargets integration with tractability and genetic-association sections.
• Added JATS-aware PMC full-text extraction for article detail views.
• MCP chart responses can now return SVG inline as a base64 image payload.
• Polished Kuva chart output with human-readable labels and KM curve improvements.
• Suppressed retry-middleware warnings from stderr.
• Pathway output now keeps section availability truthful and gives better guidance when a source lacks a section.

Fixes

• Fixed drug interaction output so supported drugs no longer return empty interaction sections.
• Fixed g:Profiler enrichment timeouts.
• Fixed the DisGeNET template crash on sparse or null payloads such as biomcp get gene KYNU disgenet. (031)
• Fixed default article retraction filtering so only confirmed retractions are excluded; PubTator3 and Semantic Scholar rows with unknown retraction status remain visible. (038)

0.8.16 — 2026-03-17

• Adopted the shared bin/lint script and wired make lint / make check to the March repo convention for Rust repos.
• Refreshed the README, homepage, CLI reference, and helper docs so the public release docs match the current BioMCP command surface.
• Expanded skills/SKILL.md for article graph helpers, enrich, batch, chart discovery, chart flags, and updated drug interaction guidance.
• Updated the Kuva chart blog post with checked-in SVG outputs for all nine worked examples plus placeholder references for terminal screenshots.
• Added Semantic Scholar article enrichment and helpers for TLDR, citations, references, and recommendations.
• Added Kuva-backed study chart rendering plus chart discovery/docs for SVG study outputs.
• Trial search now accepts fractional ages such as 0.5 years.
• Generated _meta.next_commands now pass a parser-level validity gate, and article JSON guidance is cleaner and more truthful.
• Fixed federated article search offset and sort semantics with correctness coverage.
• Breaking MCP runtime change: renamed the MCP execution tool from shell to biomcp; update MCP clients and demos to call biomcp after tools/list.
• Added CITATION.cff and citation pointers in the README and public docs.
• Fixed Semantic Scholar references to use cited papers instead of referenced papers.
• Fixed article search timeouts on --exclude-retracted.
• Fixed article retraction filtering and unary NOT parsing.
• Stabilized CTGov trial pagination and age-filtered totals: improved cursor behavior, aligned count/search params, clarified trial-filter guidance, and exposed approximate age-only counts when exact totals are too expensive.
• Expanded release-quality gates with contracts CI, version-sync checks, a PR-gated spec suite, stable/smoke lane splitting, and protein entity spec coverage.
• Updated lockfiles for the quinn-proto and PyJWT vulnerability advisories.
• Refined the Streamable HTTP demo into a tested end-to-end BRAF/melanoma workflow with a focused README and Python 3.11 compatibility.

0.8.15 — 2026-03-11

• Fixed the planning-docs CI path regression so release validation uses the repo-local planning fixtures by default instead of an Ian-local absolute path. This is the fix from PR #191 that unblocks release packaging on GitHub Actions.
• Refreshed the public discovery docs so search all is taught as the unified cross-entity entry point in the README and docs index. This is the docs alignment from PR #190.

0.8.14 — 2026-03-10

• Promoted remote Streamable HTTP in newcomer docs with a dedicated getting-started page for biomcp serve-http.
• Added a runnable PEP 723 demo client at demo/streamable_http_client.py for /mcp, including a tools/list flow and biomcp version tool call.
• Surfaced the canonical remote HTTP routes more prominently across public docs: /mcp, /health, /readyz, and /.
• Kept serve-sse migration guidance visible while shipping the Streamable HTTP release/docs/demo verification package together.
• Reranked disease search results so exact-match canonical names surface first.
• search article now rejects unsupported identifiers with explicit contract guidance instead of falling through ambiguously.
• Defaulted article search sorting to relevance across CLI entry points.
• Normalized search aliases, identifiers, and trial phase semantics across entity searches.
• Broadened trial mutation matching across title, summary, keyword, and eligibility fields.
• Removed stale skill-discovery UX and refreshed list / help output to match the shipped CLI surface.

0.8.13 — 2026-03-09

• study survival now reports Kaplan-Meier median survival, 1/3/5-year survival landmarks, and two-group log-rank p-values.
• Fixed survival median calculation: replaced raw follow-up median with Kaplan-Meier median survival.
• study compare --type expression now reports Mann-Whitney U and p-value.
• Added study download <study_id> and study download --list for local cBioPortal datahub installs.
• Hardened study download: no total body timeout for large archives, path-like study ID rejection, stream-to-disk download, and cleanup on failed extraction.
• Refreshed skills/SKILL.md with real study command usage, including cohort, filter, and survival --endpoint examples.

0.8.12 — 2026-03-07

• Added study subcommand: local cBioPortal study adapters with CLI query surface (download, cohort, survival, compare).
• Added study filter: multi-omics cross-table sample joins across mutation, CNA, expression, and clinical data.
• Added Fisher exact p-values to co-occurrence pair analysis.
• Added skill installer auto-discovery: scans existing agent config directories in priority order and supports the .agents/skills/ cross-tool standard.
• Refreshed skill guidance and reference material: adopted the measured SKILL.md refresh and added drift validation for examples, schemas, and jq snippets.
• CLI quality pass: positional search arguments, multi-token input handling, variant fallback, NCT ID validation, bare-entity shortcuts, staged trial fill, article request timeout, and --until alias.

0.8.11 — 2026-03-06

• Added expression section to gene output (GTEx tissue-specific TPM data).
• Added druggability section to gene output (DGIdb drug-gene interactions and categories).
• Added clingen section to gene output (gene-disease validity and dosage sensitivity).
• Added evidence URLs (_meta.evidence_urls) to all entity output — includes Ensembl, OMIM, NCBI Gene, and UniProt links where available.
• Added spec/ BDD documentation suite with 54 passing executable specifications.
• Unified article search: fan-out across PubTator3 and Europe PMC in parallel with PMID deduplication, source-grouped rendering, and --source <all|pubtator|europepmc>.
• Added infinite cache mode via BIOMCP_CACHE_MODE=infinite for offline/demo workflows.
• Consolidated CI into a single job; streamlined release pipeline.
• Added reusable presentations infrastructure with an intro deck, branded theme assets, and slide templates for BioMCP talks.
• Hardened PyPI release packaging for arm64 and portable version syncing in the release workflow.

0.8.10 — 2026-03-04

• Polished search all output: GWAS trait relevance filtering, clinical significance sorting, uninformative variant suppression.
• Gene-anchored article search via GENE_PROTEIN field for higher precision.
• Added trial search improvements (--mutation boolean handling and --criteria support).
• Added PyPI trusted publisher setup and release workflow updates.

0.8.9 — 2026-03-03

• Added search all cross-entity command — parallel fan-out across major entities (genes, variants, diseases, drugs, trials, articles, pathways, PGx, GWAS, and adverse events) with counts-first display and HATEOAS deep-dive links.

0.8.8 — 2026-03-02

• Output cleanup across entity renderers for consistent markdown formatting.
• Improved help discoverability and completeness across all subcommands.
• Rewrote footer output with streamlined next-step suggestions.

0.8.7 — 2026-02-27

• Improved help text discoverability and completeness for all CLI subcommands.

0.8.6 — 2026-02-27

• Fixed trial filter accuracy: age-based post-filtering, exclusion-criteria detection, and pathway source correctness.

0.8.5 — 2026-02-26

• Fixed install.sh to resolve latest tag to a release that has downloadable assets.
• Hardened input safety with SSRF prevention on user-supplied URLs.
• Enforced pagination and validation contracts across search endpoints.

0.8.4

• Simplified CI/CD workflow triggers to avoid redundant post-merge runs.
• Added runner-aware actions/cache@v4 protoc caching in CI, docs deploy, and release workflows.
• Pinned workflow protoc installation to 28.3 with cache-aware conditional setup.

0.8.3

• Added inclusion-first eligibility post-filtering to reduce exclusion-only false positives in trial matching.
• Applied cryptography dependency security updates and refreshed release artifacts.
• Tightened CLI/docs consistency around trial filter behavior and output contracts.

0.8.2

• Added location-level facility and geo post-filtering for more accurate trial site matching.
• Embedded git tag version metadata in the binary for reliable biomcp version output.
• Improved pagination and result-window handling across search command families.

0.8.1

• Expanded clinical-grade trial filtering with ~45 new search flags and validation rules.
• Added MCP tool auto-generation to reduce drift between CLI capabilities and server tool surface.
• Upgraded help/discoverability content and list-based guidance for agent-driven workflows.

0.8.0

Complete rewrite from Python to Rust. Single static binary, no runtime dependencies.

Highlights

• Single-binary CLI and MCP server — no Python, no pip, no virtual environments
• 15 biomedical data sources, unified command grammar, compact markdown output
• 14 embedded skills (guided investigation workflows)
• MCP server (stdio + SSE) with tool and resource support
• HTTP proxy (serve-http) for multi-worker shared rate limiting
• Production installer with SHA256 verification (5 platforms)
• Progressive disclosure: search returns summaries, get returns full detail with selectable sections
• NCBI API key support for improved rate limits
• 429 retry with Retry-After backoff

Data sources

MyGene.info, MyVariant.info (ClinVar, gnomAD, CIViC, OncoKB), ClinicalTrials.gov, NCI CTS API, PubMed/PubTator3, MyChem.info, Monarch/MONDO, Reactome, UniProt, OpenFDA FAERS, PharmGKB/CPIC, GWAS Catalog, Monarch (phenotypes), AlphaGenome (gRPC).

Breaking changes from Python BioMCP

• Python package biomcp-python is no longer maintained
• MCP tool names and signatures have changed
• Configuration via environment variables only

0.7.3

Legacy Python BioMCP. See branch python-0.7.3 for source code.