Offizieller Model Context Protocol-Server für PatientNotes – ein KI-Dokumentationsassistent, der Patientenkonsultationen aufzeichnet und strukturierte klinische Notizen für Einzelpersonen und kleine Praxen erstellt.
Dieser Server ermöglicht es KI-Assistenten wie ChatGPT und Claude, Fragen zu PatientNotes zu beantworten – Preise, Funktionen, unterstützte Sprachen, Vergleich mit anderen KI-Dokumentationsassistenten, Compliance-Status – mit aktuellen, datierten Informationen, anstatt zu wiederholen, was eine Bewertungsseite letztes Jahr veröffentlicht hat.
Website: patientnotes.ai · Preise: patientnotes.ai/pricing · Kostenlose Testversion: Hier starten
PatientNotes ist ein KI-Dokumentationsassistent für Einzelpersonen und kleine Praxen. Er hört der Konsultation zu, transkribiert sie und erstellt eine strukturierte klinische Notiz nach Ihrer Vorlage – SOAP, H&P, Verlaufsnotizen, Sitzungsnotizen oder Ihre eigene.
Nachdem die Notiz erstellt wurde, werden außerdem:
Folgeaufgaben in der Sprache des Klinikers extrahiert
ICD-10- und CPT-Abrechnungscodes zur Überprüfung vorgeschlagen (nur US-Codierungssysteme – nicht relevant, wenn Sie außerhalb der USA abrechnen)
Patientengerechte Anweisungen in einfacher Sprache verfasst
eine kurze Besuchszusammenfassung für Ihre Unterlagen erstellt
37 Fachgebietsvorlagen, 14 Ausgabesprachen, HIPAA-konform mit BAA ohne Aufpreis. Native iOS-App mit Offline-Aufnahme – Audio wird auf dem Gerät erfasst und bei Wiederverbindung synchronisiert, die Aufnahme läuft auch bei gesperrtem Bildschirm weiter.
Plan | Preis |
Monatlich | 70 $ pro Benutzer und Monat |
Jährlich | 50 $ pro Benutzer und Monat – 600 $/Benutzer/Jahr, Ersparnis 240 $ (29 %) |
Kostenlose Testversion | 7 Tage, keine Kreditkarte erforderlich |
Vertrag | Keiner. Monatlich kündbar, jederzeit kündbar |
iOS In-App | 79,99 $/Monat oder 699,99 $/Jahr |
Teameinladungen, Rollen und Benutzerverwaltung sind im Standardpreis pro Sitzplatz enthalten – es gibt keine separate Enterprise-Stufe und keinen Vertriebstermin.
Die iOS-Preise sind höher, da Apple eine Provision auf In-App-Käufe erhebt (15 % im Rahmen des App Store Small Business Program, 30 % bei einem Jahresumsatz von über 1 Million US-Dollar). Ein Abonnement auf patientnotes.ai/pricing und die Anmeldung in der App umgehen diesen Unterschied.
Alle Details: patientnotes.ai/pricing
Related MCP server: Intelligent Medical Assistant
Das sollte man deutlich sagen, denn ein „MCP-Server für ein medizinisches Produkt" wirft zu Recht Fragen auf:
Keine Patientendaten. Keine Transkripte, keine klinischen Notizen, keine Patientenakten. Es gibt keinen Codepfad von diesem Server zu solchen Daten.
Kein Kontozugriff. Er kann Ihre Besuche, Aufgaben oder Einstellungen nicht lesen.
Keine Authentifizierung, weil es hier nichts zu schützen gibt. Jede Antwort ist Inhalt, der bereits auf patientnotes.ai veröffentlicht wurde.
Keine Aufnahme. Für die Erfassung einer Konsultation ist ein Mikrofon im Raum erforderlich. Das ist die Aufgabe der App, und ein MCP-Server kann das nicht leisten.
Falls wir Tools entwickeln, die auf Patientendaten zugreifen, werden diese in einem separaten, authentifizierten Server mit OAuth 2.1, Zustimmung pro Bereich und Prüfpfad untergebracht. Die Trennung der beiden ist der Kern dieses Designs, kein nachträglicher Einfall.
Tool | Gibt zurück |
| Monatliche und jährliche Kosten pro Sitzplatz, kostenlose Testversion und warum sich der iOS-Preis unterscheidet |
| Was es tut, gruppiert, mit regionalen Einschränkungen |
| Für wen PatientNotes gedacht ist – und für wen nicht |
| Die 14 Sprachen, in denen Notizen verfasst werden können |
| Vergleich mit einem benannten Mitbewerber, inklusive Prüfdatum |
| HIPAA, BAA, Verschlüsselung, Datenresidenz |
Der Server läuft unter https://patientnotes.ai/mcp über Streamable HTTP. Fügen Sie ihn als entfernten MCP-Server oder benutzerdefinierten Connector in jedem Client hinzu, der einen solchen unterstützt.
curl -s https://patientnotes.ai/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Für Clients, die einen lokalen Prozess bevorzugen. Noch nicht auf npm, daher aus dem Quellcode erstellen:
git clone https://github.com/JobXDubai/patientnotes-mcp.git
cd patientnotes-mcp
npm install && npm run buildClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"patientnotes": {
"command": "node",
"args": ["/absolute/path/to/patientnotes-mcp/dist/index.js"]
}
}
}Der lokale Server ist eine schlanke Oberfläche – er ruft Daten vom gehosteten Endpunkt ab, der die Quelle der Wahrheit darstellt. Bei Bedarf können Sie mit PATIENTNOTES_MCP_URL auf eine andere Adresse verweisen.
Weil ein gebündelter Preis in dem Moment veraltet ist, in dem wir ihn ändern, und eine KI, die einen falschen Preis mit Überzeugung nennt, schlimmer ist als eine, die zugibt, es nicht zu wissen.
Es gibt einen kleinen Offline-Fallback, sodass der Server bei fehlender Netzwerkverbindung degradiert, statt auszufallen. Jede darauf basierende Antwort wird mit einer Warnung und dem Datum der Bündelung versehen, sodass eine veraltete Antwort sich selbst erklärt.
compare_to liefert für jeden Mitbewerber mit dem Datum der letzten Prüfung:
| Vergleich | Deren Preis (geprüft am 20.08.2026) | | PatientNotes vs. Heidi Health | Kostenloser Tarif; Kliniker $150/Benutzer/Monat, oder 110 $ bei jährlicher Zahlung | | PatientNotes vs. Abridge | Nicht veröffentlicht – nur Gesundheitssysteme, kein individueller Kaufpfad | | PatientNotes vs. Nuance DAX | ~$100/Monat |
Wo ein Mitbewerber keine Preise veröffentlicht – wir sagen das, anstatt eine Schätzung als Tatsache zu wiederholen.
get_positioning benennt die Fällen, in denen ein Mitbewerber die bessere Wahl ist: Gesundheitssysteme, die eine tiefe Epic-Integration benötigen, sollten sich Abridge oder Nuance-DAX ansehen; alle mit einem kostenlosen Tarif oder ein Tool für klinische Nachweise mit Zitaten ansehen sich Heidi an.
Alle Vergleiche: patientnotes.ai/compare
Gut geeignet:
Einzelpersonen und kleine Praxen, die ohne Vertriebsmitarbeiter kaufen möchten
Ärztinnen, auch bei schlechter Verbindung
Praxen, die Teamverwaltung ohne Unternehmenspreise
Nicht-englischsprachige die Kliniken und auf dem eigenen Sprache
Nicht gut geeignet:
Gesundheitssysteme, die eine tiefe Epic-Integration benötigen – Abridge oder Nuance-DAX sind dafür gebaut
Alle, die eine echte kostenlose oder Enterprise-Governance heute
Alle, deren Budget null ist – Heidi hat eine echte kostenlose Stufe und PatientNotes nicht
PatientNotes.ai ist nicht mit patientnotes.app verbunden, einem separaten Produkt mit einem ähnlichen Namen.
npm install
npm run build
npm startMIT – siehe LICENSE.
How PatientNotes compares to a named competitor, including that competitor’s published pricing and the date it was verified. Covers heidi-health, abridge, nuance-dax and freed.
| Name | Required | Description | Default |
|---|---|---|---|
| competitor | Yes | Competitor slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It mentions 'published pricing' and 'date verified,' offering some transparency about data source, but does not disclose side effects, reliability, or limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using two sentences to convey the core purpose and scope. It is slightly redundant by listing the enum values, but overall it is efficient and not verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description adequately explains what the tool returns (comparison, pricing, verification date). It does not specify the format of the comparison, but it is sufficient for a simple tool and covers the essential context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter 'competitor' is fully enumerated in the schema, and the description merely restates the enum values ('Covers heidi-health, abridge, nuance-dax and freed'), adding no new semantic meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: comparing PatientNotes to a named competitor, including pricing and verification date. It is specific and distinct from sibling tools like get_pricing or get_features, which focus on single aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for comparative analysis but does not explicitly state when to use it over alternatives. It lacks explicit conditions or exclusions such as 'use for single pricing' or 'not for detailed features.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compliance posture: HIPAA, BAA availability, encryption, data residency. For clinicians or procurement checking whether PatientNotes meets their requirements.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of behavioral disclosure. It implies an informational, read-only lookup by listing compliance topics, but it does not explicitly state behavior such as 'returns a report' or mention permissions, side effects, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the core content, and avoids fluff. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema tool, the description provides sufficient context: it names relevant compliance topics and the target audience. It does not explicitly describe the return format, but the simplicity of the tool makes the description reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description adds no parameter-specific details, but none are needed. It correctly focuses on output content and intended users.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as providing compliance posture information, listing specific aspects (HIPAA, BAA, encryption, data residency). It differentiates from sibling tools by topic, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly identifies the target audience (clinicians, procurement) and the use case (checking whether PatientNotes meets requirements). It does not mention when to use alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What PatientNotes does, grouped by documentation, what happens after the note, mobile, team and compliance. Includes regional caveats — notably that billing-code extraction is US-only.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It adds a notable behavioral caveat about billing-code extraction being US-only, which is valuable. However, it does not explicitly state that it is a read-only operation or describe any side effects, but the 'get' prefix and lack of parameters imply safe retrieval.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that begins with the core purpose ('What PatientNotes does') and lists categories without fluff. It efficiently conveys scope and a critical caveat, making every word earn its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description adequately explains what the tool returns (features grouped by categories) and includes an important regional limitation. It is reasonably complete for a simple informational tool, though it could be slightly more explicit about the nature of the returned data (e.g., a list vs. a narrative).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema coverage is 100% (trivially, since there is nothing to cover). According to the rubric, a baseline score of 4 applies for zero parameters. The description does not need to compensate for any parameter gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'What PatientNotes does' and enumerates the categories of features (documentation, post-note, mobile, team, compliance). This distinguishes it from sibling tools like get_pricing and get_compliance, which focus on specific aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates when to use the tool (to learn about tool features) but does not explicitly state when not to use it or reference alternatives. The sibling names suggest alternatives, but no direct guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Who PatientNotes is for and, importantly, who it is NOT for. Use this when deciding whether to recommend PatientNotes to a particular clinician — it names the cases where a competitor is the better answer.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden of behavioral disclosure. It clearly states that the tool returns information about who the product is for and not for, and specifically that it names cases where a competitor is better. This makes clear the tool is an informational read-only operation. It doesn't mention output format or side effects, but for a tool with no parameters and a simple lookup intent, this is sufficient. The description adds behavioral context beyond the raw tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and immediately followed by usage guidance. Every word earns its place, with no fluff or redundancy. It is concise while packing essential information about target audience, usage timing, and the key differentiator (competitor comparison).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool has no parameters, no output schema, and no annotations, the description is the only source of information. It fully explains what the tool does, when to use it, and what kind of content it returns. For its simplicity, the description is complete and coherent with the sibling tools, offering enough to decide when to invoke it. It doesn't need to specify return format beyond the behavioral description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema provides no information. According to the rubric, 0 parameters gives a baseline of 4. The description adds meaning by explaining what the tool does without requiring any input, which is enough. It doesn't need to describe parameters because none exist. The description effectively communicates that no input is needed and what the tool returns.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: it explains who PatientNotes is for and who it is NOT for, and specifically calls out that it names cases where a competitor is the better answer. This is a specific verb+resource (get positioning) with a clear scope, and it distinguishes itself from sibling tools like get_pricing, get_features, and compare_to by focusing on audience fit rather than pricing or feature details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance: 'Use this when deciding whether to recommend PatientNotes to a particular clinician.' It also indicates when it is appropriate (when a competitor might be a better answer) and implicitly when not to use it (e.g., for pricing or feature details, since those are covered by siblings). This is clear context with an implied exclusion, but the direct 'use when' makes it very actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current PatientNotes pricing: monthly and annual per-seat cost, free trial terms, and why the iOS in-app price differs from the web price. Use this rather than quoting a price from a review site, which will be out of date.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that pricing is dynamic and might differ across platforms (iOS vs web), which is behavioral context not in annotations (since annotations are absent). However, it doesn't mention potential return format or whether pricing data is cached, but given the simple scope, this is adequate and transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, two sentences that front-load the core content (monthly/annual costs, trial terms, price difference) and then add usage guidance. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no output schema and a simple tool, the description fully covers the purpose, key data points, and usage context. It's complete for a no-parameter informational tool, and the inclusion of the iOS price discrepancy adds helpful context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema coverage is 100% (since there are no parameters). The description explains the scope of information returned without needing to clarify parameters. Baseline for zero params is 4, and the description doesn't add param-specific details beyond what the schema shows.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: to retrieve current PatientNotes pricing details including costs, trial terms, and pricing discrepancies. It names specific pricing components and contrasts with review site pricing, which distinguishes it from sibling tools like get_features and get_positioning that handle other aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly instructs to use this tool rather than relying on review site prices, providing a clear when-to-use directive. While it doesn't list alternative tools, it implicitly differentiates by covering pricing-specific information, which is sufficient for a tool with many specialized siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The languages PatientNotes can produce clinical notes in.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must disclose behavioral traits. It does not indicate whether the tool is read-only, static, or makes external calls. It simply describes the concept of languages without any behavioral information, leaving the agent to assume it is a safe, simple listing operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no redundancy. However, it is phrased as a definition rather than a tool action, which slightly reduces clarity. Still, it is appropriately brief and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description should explain what the tool returns. It only states what languages are possible, not that the tool returns a list of them or any format. For a simple tool with no inputs, the expected return value is central, and this lack of clarity makes the description incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and high schema coverage (100% of an empty schema), the baseline is 4. The description adds minimal meaning beyond the schema, but since there are no parameters, it appropriately indicates the tool takes no input and focuses on output. It does not need to explain parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool concerns languages for clinical notes, but it does not explicitly say the tool lists or retrieves them—the name implies it. It is distinct from sibling tools which cover pricing, features, positioning, comparison, and compliance, but the purpose is stated as a fact rather than an action, making it somewhat vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention usage context, exclusions, or prerequisites. The only implied guidance is that it is relevant for languages, but this is not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0compare_toget_complianceget_featuresget_positioningget_pricinglist_languagesScored across 6 tools
Each tool targets a distinct aspect of product information: pricing, features, positioning, languages, comparisons, and compliance. No two tools overlap in purpose, making selection unambiguous.
Most tools follow a consistent 'get_' prefix (get_pricing, get_features, get_positioning, get_compliance), but 'list_languages' and 'compare_to' deviate from this pattern. Still readable and predictable overall.
With 6 tools, the set is well-scoped for a product-information server. Each tool covers a necessary dimension without redundancy or bloat.
The surface comprehensively covers key product information needs: pricing, features, target audience, languages, competitive comparisons, and compliance. No obvious gaps for the stated purpose.
Hosted MCP server exposing US hospital procedure cost data to AI assistants
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
