Connection check
verified live · 28h ago
phasefolio
Biotech rNPV/PoS engine for AI agents. Signed exports, evidence register, asset landscape.
Tools
13
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http, stdio
Last checked
28h ago
Tools & capabilities
13 toolsRead from the running server on 28h ago.
get_dossier
read-only
scenario_id*
Fetch the structured asset snapshot JSON for a scenario — the same content rendered in the PDF/Excel exports, in machine-readable form. Includes verdict, drivers, assumptions, evid… Fetch the structured asset snapshot JSON for a scenario — the same content rendered in the PDF/Excel exports, in machine-readable form. Includes verdict, drivers, assumptions, evidence summary, and (if available) signed-export hashes pointing to the latest signed artifacts.
get_evidence
read-only
scenario_id*
Fetch the evidence register entries for a scenario — the citations, sources, and supporting documents the analyst attached to back the assumptions. Use this when an analysis questi… Fetch the evidence register entries for a scenario — the citations, sources, and supporting documents the analyst attached to back the assumptions. Use this when an analysis question references 'what's the evidence for X?'
get_methodology
read-only
section*
Fetch a PhaseFolio methodology section's full content (rNPV engine, backtest, PoS calibration, IRA framework, development paths, clinical stage normalization, evidence standards, n… Fetch a PhaseFolio methodology section's full content (rNPV engine, backtest, PoS calibration, IRA framework, development paths, clinical stage normalization, evidence standards, network benchmarks, COGS benchmark, SG&A benchmark, tax benchmark, SEC EDGAR deal-term extraction). Designed for citation: each section has a stable URL and a methodology version identifier you can reference in analysis output.
get_project
read-only
project_id*
Fetch a PhaseFolio project's metadata: indication, sub-indication, modality, biomarker, asset name, and stage at entry. Use this when you need to ground an analysis question in the… Fetch a PhaseFolio project's metadata: indication, sub-indication, modality, biomarker, asset name, and stage at entry. Use this when you need to ground an analysis question in the project's clinical context before fetching scenarios.
get_scenario
read-only
scenario_id*
Fetch a PhaseFolio scenario's complete inputs (stage costs, durations, PoS, commercial assumptions, IRA settings) and computed outputs (eNPV, rNPV, cumulative PoS, per-stage breakd… Fetch a PhaseFolio scenario's complete inputs (stage costs, durations, PoS, commercial assumptions, IRA settings) and computed outputs (eNPV, rNPV, cumulative PoS, per-stage breakdown, top sensitivity drivers). This is the authoritative engine output — every signed export ties back to this payload.
list_scenarios
read-only
limit*project_id*
List all scenarios in a PhaseFolio project. Returns scenario IDs, names, created/updated timestamps, and top-line eNPV/rNPV. Use this to discover what scenarios exist before fetchi… List all scenarios in a PhaseFolio project. Returns scenario IDs, names, created/updated timestamps, and top-line eNPV/rNPV. Use this to discover what scenarios exist before fetching one in detail.
query_benchmarks
read-only
metric*modalityindication*
Query PhaseFolio benchmark availability. Source-backed PoS benchmarks are available separately; network cost distributions and duration percentiles are planned but currently return… Query PhaseFolio benchmark availability. Source-backed PoS benchmarks are available separately; network cost distributions and duration percentiles are planned but currently return coming_soon with null estimates rather than PhaseFolio's manual planning defaults.
query_drug_risk
read-only
project_id*
Fetch human-reviewed drug-specific clinical-risk signals for a project, including biomarker quality, Phase 1 ORR flag-only data, provenance, extractor versions, and pending-review… Fetch human-reviewed drug-specific clinical-risk signals for a project, including biomarker quality, Phase 1 ORR flag-only data, provenance, extractor versions, and pending-review counts. Use this before interpreting engine 2.6.0 drug-specific multipliers or flags.
query_evidence_atlas
read-only
limit*sub_indication*include_unverified*
Fetch the published Evidence Atlas program universe for a sub-indication. Defaults to source-verified rows from public CT.gov + FDA; agent-labeled rows require include_unverified=t… Fetch the published Evidence Atlas program universe for a sub-indication. Defaults to source-verified rows from public CT.gov + FDA; agent-labeled rows require include_unverified=true and remain explicitly labeled. Pending AI-serviced event_links are human_verified=false and review_status=pending_human_review until reviewed. Trial summaries and financial_links are source-derived facts; interpreted efficacy, PoS, and verdicts are not returned.
query_landscape
read-only
project_id*phase_filter*recency_years*
Fetch the asset-anchored competitive landscape for a project — comparable trials, competing programs, sponsor activity, and biomarker overlap. Sourced from CT.gov + FDA + PhaseFoli… Fetch the asset-anchored competitive landscape for a project — comparable trials, competing programs, sponsor activity, and biomarker overlap. Sourced from CT.gov + FDA + PhaseFolio's curated enrichment. Use when an analysis question asks 'who else is working on this?' or 'what's the competitive context?'
query_sec_deal_terms
read-only
limit*sinceuntildeal_typeindicationmin_confidence*
+1
Query SEC EDGAR deal-term extractions by indication, deal type, date range, confidence, and review state. Returns per-deal rows with source quotes and accession URLs for verificati… Query SEC EDGAR deal-term extractions by indication, deal type, date range, confidence, and review state. Returns per-deal rows with source quotes and accession URLs for verification; aggregate engine medians use the separate backend aggregate function.
triage_asset
read-only
textfields
Produce a transparent, provenance-linked CONDITIONAL READ on a drug asset for deal triage. Pass either `text` (a teaser/abstract — fields are machine-extracted and the result is ma… Produce a transparent, provenance-linked CONDITIONAL READ on a drug asset for deal triage. Pass either `text` (a teaser/abstract — fields are machine-extracted and the result is marked inputs_unconfirmed) or pre-confirmed `fields`. Returns a reasoning chain (each claim grounded or marked insufficient_evidence), mechanism-plausibility flags, PoS + landscape metrics, and a meta block with engine/methodology/synthesis versions. Does NOT compute rNPV. Not an autonomous verdict.
verify_export
read-only
hash*