DEVELOPER PREVIEW · IN DEVELOPMENT, MID-2027 · THESE PAGES DESCRIBE THE PLANNED INTERFACE
Developer preview · mid-2027
One runtime. Every interface.
Humans, pipelines and AI agents will all be clients of the same public API. The same analysis submitted through web, API, SDK, CLI or MCP resolves to the same canonical request hash — and produces the same signed evidence.
Python SDK
result = genomarker.run(
analysis="differential_expression",
spec=spec, # canonical, deterministically hashed
assurance_profile="GM-BIOMARKER-DE-1",
idempotency_key="trial-042-de-v3")
result.evidence_id # "GM-2026-08-14-8F29E1"
result.findings # structured, machine-readable
result.replay.outcome # REPRODUCED_EQUIVALENT
result.preservation.grade # "A"MCP surface — assurance only
MCP tools
list_analysis_types
get_analysis_schema
list_assurance_profiles
validate_analysis_spec
submit_analysis · get_result
get_assurance_findings
get_evidence · verify_evidence
replay_evidence
get_sap · validate_against_sapDeliberately narrow. Genomarker’s job is to assure computation — agents can gather scientific context elsewhere.
Actor provenance
Actor provenance JSON
{
"actor_type": "agent",
"interface": "mcp",
"client": "helix-sci-agent",
"model": "optional-identifier"
}