Skip to content

feat(aws-healthomics-mcp): genomics file search #1501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 43 commits into
base: main
Choose a base branch
from
+22,301 −49
Open

feat(aws-healthomics-mcp): genomics file search #1501

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
43 commits
Select commit Hold shift + click to select a range
3a955ad
feat: add core data models for genomics file search
markjschreiber Oct 7, 2025
918e521
feat(search): implement pattern matching and scoring engine
markjschreiber Oct 7, 2025
2945749
feat: implement file association detection system
markjschreiber Oct 7, 2025
27b3e36
feat: implement S3 search engine with configuration management
markjschreiber Oct 7, 2025
a62f7a1
feat:(search) adds a search interface to the healthomics sequence and…
markjschreiber Oct 7, 2025
5e6623b
feat(genomics-search): implement search orchestrator and MCP tool han…
markjschreiber Oct 7, 2025
52e0261
feat(search): adds result ranking and response assembly
markjschreiber Oct 7, 2025
30254d0
docs: add genomics file search capabilities to README and CHANGELOG
markjschreiber Oct 7, 2025
5eca2a7
Fix SearchGenomicsFiles tool: regex patterns, S3 client calls, and fi…
markjschreiber Oct 8, 2025
aa4dd8a
perf(s3-search): optimize S3 API calls with lazy loading, caching, an…
markjschreiber Oct 8, 2025
ddd784f
Fix genomics file search for HealthOmics reference stores
markjschreiber Oct 8, 2025
7ba4bbe
feat(search): enhance HealthOmics sequence and reference store search…
markjschreiber Oct 8, 2025
5f6407e
feat: performance improvements and minor fixes
markjschreiber Oct 9, 2025
1d1484c
feat: implement efficient storage-level pagination for genomics file …
markjschreiber Oct 9, 2025
bc9dfb6
fix: correct the associate of bwa files and fix pyright type errors
markjschreiber Oct 9, 2025
65c6826
feat(tests): implement comprehensive testing framework with MCP Field…
markjschreiber Oct 10, 2025
0f93475
fix(tests): repair healthomics search engine tests
markjschreiber Oct 10, 2025
a64c8d5
test(s3): add comprehensive tests for S3SearchEngine
markjschreiber Oct 10, 2025
119c998
fix(tests): fix failing healthomics search engine tests
markjschreiber Oct 10, 2025
317e389
test(result-ranker): achieve 100% test coverage for ResultRanker
markjschreiber Oct 10, 2025
49cd8b9
test(json-response-builder): achieve 100% test coverage for JsonRespo…
markjschreiber Oct 10, 2025
2b94eee
test(config-utils): achieve 100% test coverage for config utilities
markjschreiber Oct 10, 2025
194fbca
feat(s3-utils): optimize bucket validation and achieve 99% coverage
markjschreiber Oct 10, 2025
0364e5c
feat(genomics-search-orchestrator): achieve 49% test coverage with co…
markjschreiber Oct 10, 2025
c0b91d4
perf(genomics-search-orchestrator): optimize test performance by 94%
markjschreiber Oct 10, 2025
205883a
feat(healthomics-search-engine): improve test coverage from 61% to 69%
markjschreiber Oct 10, 2025
2c8d7d1
fix: clean up files and reformats some files failing lints
markjschreiber Oct 10, 2025
a80a1e0
Merge remote-tracking branch 'upstream/main' into feature/genomics-fi…
markjschreiber Oct 10, 2025
3a93788
security: fix bandit security issues
markjschreiber Oct 10, 2025
2843406
fix(tests): mock AWS account/region methods to prevent credential access
markjschreiber Oct 10, 2025
0a8c6a1
fix: fix pyright issues
markjschreiber Oct 10, 2025
5010d5e
feat: improve test coverage
markjschreiber Oct 10, 2025
298acc4
feat: increases coverage of pagination logic, filtering, fallbacks an…
markjschreiber Oct 10, 2025
23f8a51
fix: mock aws credentials
markjschreiber Oct 10, 2025
afa8b02
feat: improve test coverage of exception handling, continuation token…
markjschreiber Oct 10, 2025
9cd825b
fix: pyright type error fixed
markjschreiber Oct 10, 2025
7c48aca
feat: more test coverage to stop codecov nagging me
markjschreiber Oct 10, 2025
8049bea
feat: improvements to branch coverage
markjschreiber Oct 10, 2025
f82a873
fix(search): enforce S3 bucket access validation in orchestrator
markjschreiber Oct 17, 2025
1a78421
refactor: rename config_utils to search_config and reorganize models
markjschreiber Oct 20, 2025
ebd02bc
Merge remote-tracking branch 'upstream/main' into feature/genomics-fi…
markjschreiber Oct 20, 2025
a8e29c6
feat: comprehensive test coverage improvements and code quality enhan…
markjschreiber Oct 22, 2025
3b7c3ad
Merge branch 'main' into feature/genomics-file-search
markjschreiber Oct 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions package-lock.json
View file
Open in desktop
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this file needed?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It has benefits above and beyond uv-requirements.txt as it lets CI/CD build with the exact packages used by the developer. It looks like several other servers in the monorepo do also have uv.lock files and they are tracked by git. Maybe something for the maintainers to make a repo wide decision on (and maybe also add to the .gitignore for the whole repo)?

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

9 changes: 9 additions & 0 deletions src/aws-healthomics-mcp-server/CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

### Added

- **Genomics File Search Tool** - Comprehensive file discovery across multiple storage systems
- Added `SearchGenomicsFiles` tool for intelligent file discovery across S3 buckets, HealthOmics sequence stores, and reference stores
- Pattern matching with fuzzy search capabilities for file paths and object tags
- Automatic file association detection (BAM/BAI indexes, FASTQ R1/R2 pairs, FASTA indexes, BWA index collections)
- Relevance scoring and ranking system based on pattern match quality, file type relevance, and associated files
- Support for standard genomics file formats: FASTQ, FASTA, BAM, CRAM, SAM, VCF, GVCF, BCF, BED, GFF, and their indexes
- Configurable S3 bucket paths via environment variables
- Structured JSON responses with comprehensive file metadata including storage class, size, and access paths
- Performance optimizations with parallel searches and result streaming
- S3 URI support for workflow definitions in `CreateAHOWorkflow` and `CreateAHOWorkflowVersion` tools
- Added `definition_uri` parameter as alternative to `definition_zip_base64`
- Supports direct reference to workflow definition ZIP files stored in S3
Expand Down
Loading