Skip to content

phasefolio MCP server

com.phasefolio/phasefoliophasefolio.comstreamable-httpv0.1.4Scanned

Biotech rNPV/PoS engine for AI agents. Signed exports, evidence register, asset landscape.

10 tools: 2 change things and 8 only read.

Tools: 0 delete, 0 irreversible, 2 write, 8 read.
  • Reads private data · 1
  • Reads text others write · 10
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the phasefolio MCP server can do

The phasefolio MCP server is published by phasefolio.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (2 tools: verify_export and triage_asset), but cannot delete data. 8 tools only read.

1 tool reads private data (get_evidence); 10 tools bring in text other people can write (get_project, list_scenarios, get_scenario and 7 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 14, 2026, version 0.1.4.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

10 tools

Changes things 2Claude Code: ask
  • triage_assetProduce a transparent, provenance-linked CONDITIONAL READ on a drug asset for deal triage.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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 metrics, and a meta block with model/methodology/synthesis versions. Does NOT compute rNPV. Not an autonomous verdict.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Triage Asset
  • verify_exportVerify a signed PhaseFolio export by content hash.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Verify a signed PhaseFolio export by content hash. Returns verification status (valid/tampered/unknown), issued timestamp, methodology version, and an anonymized originating-org identifier. Use this when a user shares a PhaseFolio asset snapshot and you want to confirm it's authentic before citing the analysis.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Verify Signed Export
Only reads 8Show 8 read-only tools
  • get_dossierFetch the structured asset snapshot JSON for a scenario — the same content rendered in the PDF/Excel exports, in machine-readable form.Reads text others writeNo findings

    Why it is in this group

    • The name "get_dossier" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get Asset Snapshot
  • get_evidenceFetch the evidence register entries for a scenario — the citations, sources, and supporting documents the analyst attached to back the assumptions.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_evidence" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "document": it reads documents.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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?'

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get Evidence
  • get_methodologyFetch a PhaseFolio methodology section's full content (rNPV model, backtest, PoS calibration, IRA framework, development paths, deal-term modelling, holding valuation, clinical sta…Reads text others writeNo findings

    Why it is in this group

    • The name "get_methodology" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch a PhaseFolio methodology section's full content (rNPV model, backtest, PoS calibration, IRA framework, development paths, deal-term modelling, holding valuation, 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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get Methodology Section
  • get_projectFetch a PhaseFolio project's metadata: indication, sub-indication, modality, biomarker, asset name, and stage at entry.Reads text others writeNo findings

    Why it is in this group

    • The name "get_project" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get Project
  • get_scenarioFetch a PhaseFolio scenario's complete inputs (stage costs, durations, PoS, commercial assumptions, IRA settings) and computed outputs (eNPV, rNPV, cumulative PoS, per-stage breakd…Reads text others writeNo findings

    Why it is in this group

    • The name "get_scenario" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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 model output — every signed export ties back to this payload.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get Scenario
  • list_scenariosList all scenarios in a PhaseFolio project.Reads text others writeNo findings

    Why it is in this group

    • The name "list_scenarios" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List Scenarios
  • query_benchmarksQuery PhaseFolio benchmark availability.Reads text others writeNo findings

    Why it is in this group

    • The name "query_benchmarks" says "query": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Query Network Benchmarks
  • query_drug_riskFetch 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 …Reads text others writeNo findings

    Why it is in this group

    • The name "query_drug_risk" says "query": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "fetch" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    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 model 2.6.0 drug-specific multipliers or flags.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Query Drug-Specific Risk

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write10
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:44 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://app.phasefolio.com/api/mcp: tools/list returned 10 tools to an anonymous client, including verify_export (write), triage_asset (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http phasefolio https://app.phasefolio.com/api/mcp
claude mcp add --transport http phasefolio https://app.phasefolio.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__phasefolio__get_project",
      "mcp__phasefolio__list_scenarios",
      "mcp__phasefolio__get_scenario",
      "mcp__phasefolio__get_evidence",
      "mcp__phasefolio__get_dossier",
      "mcp__phasefolio__query_drug_risk",
      "mcp__phasefolio__query_benchmarks",
      "mcp__phasefolio__get_methodology"
    ],
    "ask": [
      "mcp__phasefolio__verify_export",
      "mcp__phasefolio__triage_asset"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as phasefolio. Review it before you use it.

Capability tags behind 10 rules
  • mcp__phasefolio__get_project untrusted-input
  • mcp__phasefolio__list_scenarios untrusted-input
  • mcp__phasefolio__get_scenario untrusted-input
  • mcp__phasefolio__get_evidence private-data, untrusted-input
  • mcp__phasefolio__get_dossier untrusted-input
  • mcp__phasefolio__query_drug_risk untrusted-input
  • mcp__phasefolio__query_benchmarks untrusted-input
  • mcp__phasefolio__verify_export untrusted-input
  • mcp__phasefolio__triage_asset untrusted-input
  • mcp__phasefolio__get_methodology untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.phasefolio/phasefolio/verify?hash=45f24b3fde940f9cf27f8ded400f6ecda0137781204cae37d44861b6906cc05d" | jq -e '.changed == false'

Pinned hash 45f24b3fde94, from Nov 14, 2026, 01:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.phasefolio/phasefolio/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.phasefolio/phasefolio
[![Anlyon Radar](https://radar.anlyon.com/badge/com.phasefolio/phasefolio.svg)](https://radar.anlyon.com/servers/com.phasefolio/phasefolio)

Source: MCP Registry. Synced Oct 21, 2026, 18:00 UTC.

phasefolio MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the phasefolio MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the phasefolio MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the phasefolio MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the phasefolio MCP server have?

10 tools: 2 write, 8 read. verify_export, triage_asset, get_project, list_scenarios, get_scenario, get_evidence, get_dossier, query_drug_risk and 2 more.

Does the phasefolio MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the phasefolio MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the phasefolio MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.