PhaseFolio

**Biotech rNPV / probability-of-success engine for AI agents.** Audit-grade asset valuation with signed dossier exports, cell-level evidence registers, and asset-anchored competitive landscape — the same engine healthcare investors and tech transfer offices use to value early-stage biotech assets, exposed directly to your AI analyst. ### Tools **Public tier — no auth required** - `query_benchmarks` — anonymized network statistics (PoS by indication × modality, cost / duration percentiles) - `verify_export` — verify a signed PhaseFolio dossier by content hash or URL; returns issued timestamp, methodology version, originating-org identifier - `get_methodology` — fetch any methodology section in citable form (backtest, PoS calibration, IRA framework, evidence standards, network benchmarks) **Bearer tier — request a token at [app.phasefolio.com/contact](https://app.phasefolio.com/contact)** - `get_project` — project metadata: indication, sub-indication, modality, biomarker, asset name, stage at entry - `list_scenarios` — scenarios in a project with top-line eNPV / rNPV - `get_scenario` — full scenario inputs + computed outputs (eNPV, rNPV, cumulative PoS, per-stage breakdown, top sensitivity drivers) - `get_evidence` — evidence-register entries: citations, sources, supporting documents, freshness - `get_dossier` — structured dossier JSON, mirroring the IC Dossier PDF / Excel exports - `query_landscape` — asset-anchored competitive landscape (comparable trials, competing programs, sponsor activity, biomarker overlap) sourced from CT.gov + FDA + curated enrichment ### Trust artifacts Every PhaseFolio dossier export carries a cryptographic signature tying file content to engine version and methodology version. AI agents can verify any artifact in one tool call. Public key at [`/.well-known/phasefolio-pubkey.pem`](https://app.phasefolio.com/.well-known/phasefolio-pubkey.pem). Methodology is fully published and citation-ready at [app.phasefolio.com/methodology](https://app.phasefolio.com/methodology). Backtested on a held-out cohort: 16 rheumatoid-arthritis programs, AUC 0.625, Wilson 95% CI on accuracy. Oncology backtest in progress. ### Sources - [Methodology hub](https://app.phasefolio.com/methodology) - [Verify a signed export](https://app.phasefolio.com/verify) - [Official MCP Registry listing](https://registry.modelcontextprotocol.io/v0/servers?search=phasefolio)