HugoScore hugoscore.org

Patient-controlled health records AI

OpenKP

This assessment covers OpenKP with a patient-chosen AI client. OpenKP itself is a local record connector, with preview and confirmation workflows. The chosen AI client receives returned records under its own policies. OpenKP and HugoScore share a maintainer, so this is a self-evaluation.

Document-based draft Read full report Open directory

Checklist assessment dated October 30, 2026. Independent confirmation is incomplete. Hugo has not personally verified this service.

Expands10 of 12 agency checks metDocument-based draft. Independent confirmation incomplete; not product-tested.How categories work

Agency checklist · October 30, 2026

Expands 10 of 12 yes

Document-based draft. Independent confirmation is incomplete. Hugo has not personally verified this service.

Assessed function: Patient-run local MCP server that lets the member's own MCP client (Claude Desktop consumer path; not tested in this review) read, and with explicit confirmation write to, their own Kaiser Permanente NorCal portal record.

Initial Anthropic coding has an Anthropic model in the role record.

A no can mean missing documentation or institution-dependent control; it does not by itself establish harmful behavior. These categories are not clinical safety or product-quality ratings.

  • Public documents do not establish actual product behavior.
  • Stored quotation missing for yes answers: 5. Evidence repair is pending.
See all twelve answers and their evidence
QuestionAnswerEvidence / reviewSource and reasoning
1. Told it is AIYesdocumented
Confirmed at document level
OpenKP is a local MCP server that lets your AI assistant read, compare, and carefully act on your Kaiser Permanente record Source

The member installs and chooses an AI assistant, and the docs call it AI throughout. There is no separate consent step.

2. Operator and model maker namedYesdocumented
Document follow-up: supported
Author: Hugo Campos Source
A compromised Anthropic API (Claude Desktop handles this, not us) Source

The public design document names Hugo Campos and identifies the Anthropic/Claude connection. Q2 requires public naming, not homepage placement or a single sentence. Applying the same standard as OwnChart changes this answer to yes. Hugo's authorship remains disclosed; it does not justify a stricter naming test.

3. Patient chooses to use itYesdocumented
Confirmed at document level
Want a richer, more agentic interface to their own health record than the kp.org website or Kaiser app provide. Source

The README's 'Who this is for' section describes members who install it themselves. Kaiser does not apply it.

4. Patient sets the taskYesdocumented
Confirmed at document level
It lets a Kaiser member ask Claude, in plain English, to read and act on their own medical record. Source

The tools return raw structured data and do not steer. DESIGN.md says 'Tools don't pre-summarize.' The README's suggested prompts are examples only.

5. Patient can decline or stopYesSelf-started rule; direct refusal wording not documented
Confirmed at document level
Quotation not recorded; evidence repair pending. Source

Yes follows the adopted Q5 rule for a self-started optional tool, rather than an explicit published refusal right. The original coder's note below predates that normalization and is retained as history: No source states that the patient can decline or stop and keep the same service. Related but not the same statements: DESIGN.md says 'Everything a member can do by clicking around kp.org, OpenKP exposes as a tool', and 'If OpenKP disappears tomorrow, the user loses nothing' (about credentials). Write actions need a preview and explicit confirm. I did not treat these as an explicit decline right.

6. Patient sees the AI outputYesdocumented
Confirmed at document level
Claude shows this to the user. Source

The statement is about write previews. Read answers appear in the patient's own client, as in the openkp.org examples. Preview and commit actions are logged in ~/.openkp/audit.log.

7. Patient can correct or challengeNonot-documented
Document follow-up: not documented in inspected sources
returns a preview without touching Kaiser Source

GitHub access is now available. The root README, design document and installation README were inspected. They document preview and confirmation of writes, but no route to correct or contest the assistant's output was found in those documents. No retained under the not-documented rule. This is a bounded document finding, not proof that conversational correction is impossible.

8. Patient can get a copyYesdocumented
Confirmed at document level
Data exports include conversation data and the user data for your account. Source

Individual-user Claude export provides a qualifying copy; deletion of all local or institutional artifacts is not established.

9. Patient can deleteYesdocumented
Confirmed at document level
which will be removed immediately from your conversation history and automatically deleted from our back-end within 30 days. Source

Host terms (Claude Desktop, Anthropic). OpenKP documents no deletion or uninstall steps for its own local files in ~/.openkp. Its audit log is described as append-only. Deleting local files is possible but not documented.

10. Training or sale does not override patient choiceYesdocumented
Confirmed at document level
We may use your Inputs and Outputs to train and improve Anthropic AI models, unless you opt out through your account settings. Source

Host terms decide, for the documented default of Claude Desktop on a consumer account. Opt-out exists, but the policy still allows use of data flagged for safety review or explicitly reported. Conflict in OpenKP's own docs: the README says 'PHI passes only between Kaiser, OpenKP on your Mac, and Claude Desktop on your Mac' and 'Everything stays on your machine.' The website's Limits section is more accurate: 'Your assistant sees tool results'. Claude Desktop sends tool results to Anthropic's cloud. A different MCP client would change this answer.

11. Patient can run it or take it elsewhereYesdocumented
Confirmed at document level
Source-available. Noncommercial license (PolyForm NC 1.0.0). Local-first. Source

The repo is public and openkp/LICENSE is PolyForm Noncommercial 1.0.0 (Required Notice: Copyright (c) 2026 Hugo Campos). The README says 'Everything stays on your machine. There is no OpenKP server' and the site says any MCP-capable client should be able to call it. The patient runs it locally with their own Kaiser credentials. It is source-available, not OSI open source. It covers Kaiser NorCal only. The site warns that automated portal access 'may conflict with Kaiser's terms of use'.

12. No advertising or data businessNodocumented
Corrected after independent review; accepted by editor
sharing your personal data for targeted advertising to promote our products and services Source

Claude consumer targeted advertising fails Q12; training alone is a separate Q10 issue.

Initial coding: Claude Sonnet helpers, compiled by Claude Opus 5.5 (Anthropic). Selective review and corrections: GPT-6 Astra (OpenAI). Editor: Hugo Campos. Acceptance of corrections is not product verification.

Checklist rules · Independent review and limitations · Later evidence follow-up

Earlier v1.3 assessment and control finding

Historical assessment under different rules. It does not set the current checklist zone.

Leans expandsEarlier review, before the published method. Documents only.

Agency finding, before method v1.3

Strongly agency-expanding

Legacy editorial placement, pre-method: 91

This profile has not yet been reviewed under the published method. Its finding and any number are editorial placements made before the method existed.

Evidence
Documentary review. Public sources only, no hands-on testing by HugoScore.
Review status
AI draft. No person has settled the findings.
The question we ask Who does OpenKP serve in this deployment?
Control Patient-run local MCP server that lets the member's own MCP client (Claude Desktop consumer path; not tested in this review) read, and with explicit confirmation write to, their own Kaiser Permanente NorCal portal record.
Agency read Expands
Vendor
OpenKP / Hugo Campos
Who it serves
Patient-directed record infrastructure with a separately chosen AI client
Primary User
Technically curious Kaiser Permanente Northern California members and patient advocates
Control Model
Local connector with a separately chosen AI client and that client’s data policies.
Patient Impact
Cross-note comparisons, access-log questions, and retrieving original records enable scrutiny of institutional accounts. The language model provides interpretation, so accuracy and critical capacity must be evaluated for the combined workflow.
Profile Status
Document-based draft
Last assessed
Oct 30, 2026
Earlier review confidence
Medium for architecture, lower for current implementation and usable approval (AI-assisted draft)
Earlier review model
OpenAI Codex / GPT-6
Earlier human review record
Hugo Campos authorized publication of these AI-assisted draft reassessments on September 8, 2026. This does not claim comprehensive human verification of every finding.

Earlier evidence and assessment

The sections below preserve the earlier review. Its classifications and provenance are historical; the checklist above gives the current draft classification.

Earlier finding · Legacy editorial placement, pre-method: 91

Method v1.3. The control line is evidence for how the agency finding arose, not a quality score. Legacy editorial placement, pre-method: 91. Not comparable with v1.3 positions.

Strongly agency-expanding

This assessment covers OpenKP with a patient-chosen AI client. OpenKP itself is a local record connector, with preview and confirmation workflows. The chosen AI client receives returned records under its own policies. OpenKP and HugoScore share a maintainer, so this is a self-evaluation.

Patient agency

How this tool changes agency

Expands agency when

Cross-note comparisons, access-log questions, and retrieving original records enable scrutiny of institutional accounts. The language model provides interpretation, so accuracy and critical capacity must be evaluated for the combined workflow.

Limits agency when

Client approval behavior, current source/version parity, external model data handling, portal terms, and accessibility outside technically capable NorCal users.

Patient agency assessment

Who sets and changes the goal?

Patient authority

The patient chooses the substantive questions and AI client, and operates the portal connector. A callable confirmation parameter is a control mechanism, but not proof that every client obtains informed human approval before invoking it.

What can the patient understand, question, or do?

Critical capacity

Cross-note comparisons, access-log questions, and retrieving original records enable scrutiny of institutional accounts. The language model provides interpretation, so accuracy and critical capacity must be evaluated for the combined workflow.

Can the patient evaluate the conditions of use?

Informed control

The website identifies the client data boundary more clearly than the repository's broad local-only statement. A source-available noncommercial license supports personal adaptation without guaranteeing universal use rights or secure operation.

Text findings

Conflict of interest

Self-evaluated: OpenKP and HugoScore share the same maintainer

Hugo Campos maintains both OpenKP and HugoScore, so this profile is a self-evaluation rather than an independent review. It is published with that label, and independent third-party review of OpenKP is invited and outstanding.

Conditions of use

Published controls and their limits

The website identifies the client data boundary more clearly than the repository's broad local-only statement. A source-available noncommercial license supports personal adaptation without guaranteeing universal use rights or secure operation.

What remains unknown?

Not tested or not established

Client approval behavior, current source/version parity, external model data handling, portal terms, and accessibility outside technically capable NorCal users.

Who evaluated this?

AI-assisted public-source draft

Vendor statements describe published conditions, not independently verified behavior. No clinical, security, accessibility, or legal validation is claimed. Earlier evidence remains dated in the report and history.

Sources checked

Source-specific findings and retrieval limitations are recorded in the full report.

Earlier review provenance

Criteria

CAIHL-derived HugoScore framework and September 7 qualitative review priorities. Draft v1.2 numerical anchors remain unadopted.

Reviewer

AI-assisted public-source reassessment prepared in OpenAI Codex.

AI / model

OpenAI Codex / GPT-6

Human review

Hugo Campos authorized publication of these AI-assisted draft reassessments on September 8, 2026. This does not claim comprehensive human verification of every finding.

Review date

2026-09-08

Limitations

Client approval behavior, current source/version parity, external model data handling, portal terms, and accessibility outside technically capable NorCal users. No live product use, patient-data upload, account creation, code audit, clinical evaluation, or independent implementation validation.

Earlier review method

Focused public-source reassessment using CAIHL: patient authority, critical capacity, and informed control. Existing evidence plus one focused primary-source pass and at most one targeted follow-up. No live product testing. Numerical scores remain provisional editorial placements, not a new calculation.

Document-based draft · Medium for architecture, lower for current implementation and usable approval (AI-assisted draft)