# WebDiet MCP server

Patient, meal plan, prescription, chart and anthropometry management for dietitians.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-mcp-dir-webdiet-mcp
- Repository: https://github.com/mcp-dir/webdiet-mcp

## Install
- Endpoint: https://api.mcp.ai/p_webdiet
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.mcp.ai/p_webdiet

## Tools
- webdiet_list_accounts - List all WebDiet accounts linked to this install.
Returns each account's id, email, label, and an "is_default" flag (true when only one is linked — no need to pass `account` in other tools). When the user wants to add another WebDiet account, return `add_account_url` (no payload) como link clicável — abre o form de login no dashboard. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_patient_list - Read patients in WebDiet.
Actions: list (search by keyword — returns id, nome, link, with pagination), get (full profile with address, phone, links to panel sections).
Both actions return a permanent "link" identifier and direct URLs when available (antropometria, prescriptions, etc.).
IMPORTANT: Patient list search may be paginated — for writes, pass the numeric id from webdiet_patient get/list, the portal "link" number, or a unique phone/name keyword; the adapter falls back to dadosPaciente.php when the id is not on the first list page.

[Flattened action: list]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_patient_get - Read patients in WebDiet.
Actions: list (search by keyword — returns id, nome, link, with pagination), get (full profile with address, phone, links to panel sections).
Both actions return a permanent "link" identifier and direct URLs when available (antropometria, prescriptions, etc.).
IMPORTANT: Patient list search may be paginated — for writes, pass the numeric id from webdiet_patient get/list, the portal "link" number, or a unique phone/name keyword; the adapter falls back to dadosPaciente.php when the id is not on the first list page.

[Flattened action: get]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_patient_write_create - Create or update patients in WebDiet.
Actions: create (nome + nascimento required — returns patient_id), update (partial fields).
IMPORTANT: nascimento (birth date DD/MM/YYYY) is REQUIRED for create — WebDiet uses it to calculate age in prescriptions. Without it, metodoPlanning.php crashes with a Fatal Error.
For destructive removal use webdiet_patient_delete.

[Flattened action: create]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_patient_write_update - Create or update patients in WebDiet.
Actions: create (nome + nascimento required — returns patient_id), update (partial fields).
IMPORTANT: nascimento (birth date DD/MM/YYYY) is REQUIRED for create — WebDiet uses it to calculate age in prescriptions. Without it, metodoPlanning.php crashes with a Fatal Error.
For destructive removal use webdiet_patient_delete.

[Flattened action: update]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_patient_delete - Permanently delete a WebDiet patient (uses removerPaciente — resolves id/link from a fresh list first). Irreversible.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_get_consultations - Load food diary entries, meal reactions, attachments, or orientations for a patient. Use tipo to select: diario (food diary), reacoes (meal reactions), anexos (attachments), orientacoes (guidelines/orientations sent to patient).

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prontuario - Get the clinical record (prontuario) for a WebDiet patient. Returns decoded text with sections: Identificacao, Triagem, Anamnese alimentar, etc.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prontuario_write - Save the clinical record (prontuario) for a WebDiet patient. Pass texto as a JSON array of HTML strings, one per section.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_anamnese - List all anamnesis records for a WebDiet patient WITH the full Q/A content.
Each item carries:
  - id, titulo, data
  - texto       → plain-text Q/A (readable, line-broken — best for AI consumption / RAG)
  - texto_html  → original HTML (<b>...</b><br>...) preserved for rich rendering
  - interpretacao / interpretacao_html → nutritionist's notes when present
WebDiet stores the answers as URL-encoded HTML (<b>question</b><br>answer<br><br>); this tool decodes both representations so the agent can read e.g. food frequency, complaints, goals, allergies for the patient.
For pre-consultation questionnaire responses NOT yet linked to a patient, use webdiet_preconsulta action=list_responses.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_anamnese_write_save - Create / update anamnesis records in WebDiet.
Actions: save (create or update — anamnese_id empty = new), save_interpretation (save AI/nutritionist interpretation), duplicate (copy existing record).
For destructive removal use webdiet_anamnese_delete.

[Flattened action: save]

Bulk support: accepts patient_ids, anamnese_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_anamnese_write_save_interpretation - Create / update anamnesis records in WebDiet.
Actions: save (create or update — anamnese_id empty = new), save_interpretation (save AI/nutritionist interpretation), duplicate (copy existing record).
For destructive removal use webdiet_anamnese_delete.

[Flattened action: save_interpretation]

Bulk support: accepts patient_ids, anamnese_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_anamnese_write_duplicate - Create / update anamnesis records in WebDiet.
Actions: save (create or update — anamnese_id empty = new), save_interpretation (save AI/nutritionist interpretation), duplicate (copy existing record).
For destructive removal use webdiet_anamnese_delete.

[Flattened action: duplicate]

Bulk support: accepts patient_ids, anamnese_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_anamnese_delete - Permanently delete an anamnesis record in WebDiet. Irreversible.

Bulk support: accepts patient_ids, anamnese_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_preconsulta_list_templates - Read pre-consultation questionnaires (Pré-consulta) in WebDiet.
Actions:
- list_templates  → list all questionnaire templates the nutritionist publishes. Each item returns nome, descricao, perguntas[] (decoded), modelo, codigo, "link" (the public short URL https://nutr.se/<short> to share with patients) and "preview_url" (panel preview). USE THIS when the user asks for "o link do questionário de pré-consulta" / "link do formulário".
- list_responses  → list patient submissions to ANY template. Each response has id, id_code, template_nome, origem (anamnese | questionario), respondedor {nome, telefone, nascimento}, data, texto (decoded plain Q/A), texto_html (original HTML), pdf_url. Use filtros tipo (template name) and nome (responder name) to narrow.
- get_response    → fetch one response by id (or id_code/codigo).
For LINKING a response to an existing patient (vincular), use webdiet_preconsulta_write action=link_to_patient.

[Flattened action: list_templates]

Bulk support: accepts response_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_preconsulta_list_responses - Read pre-consultation questionnaires (Pré-consulta) in WebDiet.
Actions:
- list_templates  → list all questionnaire templates the nutritionist publishes. Each item returns nome, descricao, perguntas[] (decoded), modelo, codigo, "link" (the public short URL https://nutr.se/<short> to share with patients) and "preview_url" (panel preview). USE THIS when the user asks for "o link do questionário de pré-consulta" / "link do formulário".
- list_responses  → list patient submissions to ANY template. Each response has id, id_code, template_nome, origem (anamnese | questionario), respondedor {nome, telefone, nascimento}, data, texto (decoded plain Q/A), texto_html (original HTML), pdf_url. Use filtros tipo (template name) and nome (responder name) to narrow.
- get_response    → fetch one response by id (or id_code/codigo).
For LINKING a response to an existing patient (vincular), use webdiet_preconsulta_write action=link_to_patient.

[Flattened action: list_responses]

Bulk support: accepts response_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_preconsulta_get_response - Read pre-consultation questionnaires (Pré-consulta) in WebDiet.
Actions:
- list_templates  → list all questionnaire templates the nutritionist publishes. Each item returns nome, descricao, perguntas[] (decoded), modelo, codigo, "link" (the public short URL https://nutr.se/<short> to share with patients) and "preview_url" (panel preview). USE THIS when the user asks for "o link do questionário de pré-consulta" / "link do formulário".
- list_responses  → list patient submissions to ANY template. Each response has id, id_code, template_nome, origem (anamnese | questionario), respondedor {nome, telefone, nascimento}, data, texto (decoded plain Q/A), texto_html (original HTML), pdf_url. Use filtros tipo (template name) and nome (responder name) to narrow.
- get_response    → fetch one response by id (or id_code/codigo).
For LINKING a response to an existing patient (vincular), use webdiet_preconsulta_write action=link_to_patient.

[Flattened action: get_response]

Bulk support: accepts response_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_preconsulta_write_link_to_patient - Vincular (link) a pre-consultation response to an existing patient in WebDiet.
Action: link_to_patient — imports the response content into the patient's chart. WebDiet routes automatically based on the response's "origem":
  • origem=anamnese      → response becomes a new anamnese (importarPreanamnese.php)
  • origem=questionario  → response becomes a new diagnostico (criarDiagnosticoPre.php)
This is the API-equivalent of the panel's "Vincular ao paciente" button on the Respostas dos questionários page. After linking, the response remains in the responses list — use webdiet_preconsulta_delete to remove it if desired.
Tip: when the response's respondedor.nome differs from the patient's nome (e.g. "DALILA JULIAO MARTINS" vs "Dalila CG"), match by telefone or nascimento via webdiet_patient list before linking.

[Flattened action: link_to_patient]

Bulk support: accepts patient_ids, response_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_preconsulta_delete - Permanently delete a pre-consultation response in WebDiet. Templates are NOT affected. Irreversible.

Bulk support: accepts response_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_antropometria_list - Read anthropometry (body measurement) records for a WebDiet patient.
Actions: list (all records with id, date, type, direct URL), get (full measurements from a specific record including weight, height, skinfolds, circumferences, bioimpedance, BMI, body fat %, classifications + direct URL).
Each record includes a "url" field with the direct link to the record in WebDiet (e.g. https://pt.webdiet.com.br/painel/v4/antropometria.php?id=...).
Use this to analyze patient body composition evolution over time. For creating/saving records, use webdiet_create_antropometria + webdiet_save_antropometria.

[Flattened action: list]

Bulk support: accepts patient_ids, antropometria_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_antropometria_get - Read anthropometry (body measurement) records for a WebDiet patient.
Actions: list (all records with id, date, type, direct URL), get (full measurements from a specific record including weight, height, skinfolds, circumferences, bioimpedance, BMI, body fat %, classifications + direct URL).
Each record includes a "url" field with the direct link to the record in WebDiet (e.g. https://pt.webdiet.com.br/painel/v4/antropometria.php?id=...).
Use this to analyze patient body composition evolution over time. For creating/saving records, use webdiet_create_antropometria + webdiet_save_antropometria.

[Flattened action: get]

Bulk support: accepts patient_ids, antropometria_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_create_antropometria - Create a new body measurement record for a patient. Returns the record ID needed for webdiet_save_antropometria. Types: adulto (adult), infantil (child), gestacional (pregnancy).

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_save_antropometria - Save body measurements (anthropometry) for a patient. Call webdiet_create_antropometria first to get the antropometria_id.
All numeric values are strings. Provide raw measurements — calculated fields (IMC, GC%, density, fat mass, lean mass, classifications) are computed automatically server-side using the chosen formula.
Sections: basic (peso/altura), skinfolds (10 dobras in mm), circumferences (20 fields in cm, bilateral pairs for limbs), bone diameters (3 fields in cm), bioimpedance (9 fields from scale).
Formulas for body fat %: pollock3 (default), pollock7, guedes, petroski, durnin, faulkner, nenhuma.
Density conversion: brozek (default) or siri. Side for CMB: esquerdo (default) or direito.

Bulk support: accepts patient_ids, antropometria_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_get_planner - Load the nutritionist's calendar/agenda for a date: appointments, overdue tasks, birthdays, events. Defaults to today. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prescription_list - Read meal plan prescriptions in WebDiet.
Actions: list (all recent prescriptions — each includes "url" with the full direct link), get_detail (full meals/foods from a prescription URL).
Always show the "url" field to the user when they ask for a prescription link.

[Flattened action: list] Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prescription_get_detail - Read meal plan prescriptions in WebDiet.
Actions: list (all recent prescriptions — each includes "url" with the full direct link), get_detail (full meals/foods from a prescription URL).
Always show the "url" field to the user when they ask for a prescription link.

[Flattened action: get_detail] Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prescription_write_create - Create, save or publish meal plan prescriptions in WebDiet.
Actions: create (new prescription for patient), save (meals/foods JSON to existing prescription), publish (release prescription to patient — makes it visible on the patient portal/app).
IMPORTANT: After creating and saving foods, you MUST call publish to make the prescription visible to the patient.

═══ MÉTODO DE PRESCRIÇÃO — escolha no create ═══
WebDiet tem 3 métodos:

• "Convencional" (UI: "Por alimentos", URL: metodoPlanning.php) — DEFAULT e RECOMENDADO. Alimento-por-alimento. Para cálculo de macros automático (proteínas/lipídios/carboidratos/calorias) na tabela "Alimentos prescritos" detalhada, cada alimento DEVE incluir o campo "id" com o WebDiet food-DB ID numérico. Sem id, o alimento AINDA é salvo no método Convencional e aparece no card expandido da refeição com nome + medida caseira, mas sem macros. NÃO vai para a seção qualitativa — o save retorna um warning explicando.

• "Equivalentes"  (UI: "Por equivalentes", URL: metodoWebdiet.php) — avançado. Prescrição por grupos de equivalentes. Requer IDs do banco.

• "Qualitativo"   (UI: "Qualitativa", URL: metodoQualitativo.php) — texto livre por refeição. A página do Qualitativo usa estrutura de dados diferente (refs com objetos cardapio) que este adapter ainda não gera corretamente via save. Para prescrições qualitativas, recomendado: criar via UI ou usar metodo="Convencional" sem food IDs (os alimentos aparecem como texto na refeição sem macros, efeito semelhante).

═══ prescricao_json (para o save) ═══
JSON array de refeições. Cada refeição: {nome, horario, alimentos:[...]}.
Cada alimento: {nome, quantidade, medida_caseira, peso_gramas, id?}.

AUTO-RESOLVE: se "id" não for enviado, o adapter procura automaticamente o melhor match no banco WebDiet (mesmo catálogo do webdiet_food_search) pelo campo "nome" e preenche o id antes de salvar — com isso os macros são calculados mesmo sem pré-chamar webdiet_food_search. O save retorna auto_resolved_foods {resolved, not_found, unresolved[]} indicando quais nomes não tiveram correspondência. Para controle fino (variante específica do banco, gramagem da medida caseira etc.), ainda é recomendado chamar webdiet_food_search e enviar o "id" explicitamente.

Para evitar duplicação na UI ("2 2 fatias (50g)"), use quantidade numérica em "quantidade" e medida_caseira SEM repetir esse número e SEM sufixo "(Xg)" — ex.: quantidade="2", medida_caseira="fatias", peso_gramas="50". O MCP também normaliza automaticamente se você enviar texto completo.

Exemplo sem ids (o adapter resolve automaticamente; nomes pouco específicos podem não encontrar match):
[{"nome":"Café da Manhã","horario":"07:00","alimentos":[{"nome":"Pão integral","quantidade":"2","medida_caseira":"fatias","peso_gramas":"60"}]}]

Exemplo com ids (pula o auto-resolve — ideal quando você já escolheu a variante exata):
[{"nome":"Almoço","horario":"12:00","alimentos":[{"id":"9153","nome":"Arroz branco cozido","quantidade":"4","medida_caseira":"4 colheres de sopa (100g)","peso_gramas":"100"},{"id":"9168","nome":"Feijão carioca cozido","quantidade":"2","medida_caseira":"2 colheres (50g)","peso_gramas":"50"}]}]

O save retorna {ok, metodo, warnings[], raw, auto_resolved_foods}. warnings avisa sobre alimentos sem id e alimentos não encontrados no banco.

[Flattened action: create]

Bulk support: accepts patient_ids, prescription_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prescription_write_save - Create, save or publish meal plan prescriptions in WebDiet.
Actions: create (new prescription for patient), save (meals/foods JSON to existing prescription), publish (release prescription to patient — makes it visible on the patient portal/app).
IMPORTANT: After creating and saving foods, you MUST call publish to make the prescription visible to the patient.

═══ MÉTODO DE PRESCRIÇÃO — escolha no create ═══
WebDiet tem 3 métodos:

• "Convencional" (UI: "Por alimentos", URL: metodoPlanning.php) — DEFAULT e RECOMENDADO. Alimento-por-alimento. Para cálculo de macros automático (proteínas/lipídios/carboidratos/calorias) na tabela "Alimentos prescritos" detalhada, cada alimento DEVE incluir o campo "id" com o WebDiet food-DB ID numérico. Sem id, o alimento AINDA é salvo no método Convencional e aparece no card expandido da refeição com nome + medida caseira, mas sem macros. NÃO vai para a seção qualitativa — o save retorna um warning explicando.

• "Equivalentes"  (UI: "Por equivalentes", URL: metodoWebdiet.php) — avançado. Prescrição por grupos de equivalentes. Requer IDs do banco.

• "Qualitativo"   (UI: "Qualitativa", URL: metodoQualitativo.php) — texto livre por refeição. A página do Qualitativo usa estrutura de dados diferente (refs com objetos cardapio) que este adapter ainda não gera corretamente via save. Para prescrições qualitativas, recomendado: criar via UI ou usar metodo="Convencional" sem food IDs (os alimentos aparecem como texto na refeição sem macros, efeito semelhante).

═══ prescricao_json (para o save) ═══
JSON array de refeições. Cada refeição: {nome, horario, alimentos:[...]}.
Cada alimento: {nome, quantidade, medida_caseira, peso_gramas, id?}.

AUTO-RESOLVE: se "id" não for enviado, o adapter procura automaticamente o melhor match no banco WebDiet (mesmo catálogo do webdiet_food_search) pelo campo "nome" e preenche o id antes de salvar — com isso os macros são calculados mesmo sem pré-chamar webdiet_food_search. O save retorna auto_resolved_foods {resolved, not_found, unresolved[]} indicando quais nomes não tiveram correspondência. Para controle fino (variante específica do banco, gramagem da medida caseira etc.), ainda é recomendado chamar webdiet_food_search e enviar o "id" explicitamente.

Para evitar duplicação na UI ("2 2 fatias (50g)"), use quantidade numérica em "quantidade" e medida_caseira SEM repetir esse número e SEM sufixo "(Xg)" — ex.: quantidade="2", medida_caseira="fatias", peso_gramas="50". O MCP também normaliza automaticamente se você enviar texto completo.

Exemplo sem ids (o adapter resolve automaticamente; nomes pouco específicos podem não encontrar match):
[{"nome":"Café da Manhã","horario":"07:00","alimentos":[{"nome":"Pão integral","quantidade":"2","medida_caseira":"fatias","peso_gramas":"60"}]}]

Exemplo com ids (pula o auto-resolve — ideal quando você já escolheu a variante exata):
[{"nome":"Almoço","horario":"12:00","alimentos":[{"id":"9153","nome":"Arroz branco cozido","quantidade":"4","medida_caseira":"4 colheres de sopa (100g)","peso_gramas":"100"},{"id":"9168","nome":"Feijão carioca cozido","quantidade":"2","medida_caseira":"2 colheres (50g)","peso_gramas":"50"}]}]

O save retorna {ok, metodo, warnings[], raw, auto_resolved_foods}. warnings avisa sobre alimentos sem id e alimentos não encontrados no banco.

[Flattened action: save]

Bulk support: accepts patient_ids, prescription_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_prescription_write_publish - Create, save or publish meal plan prescriptions in WebDiet.
Actions: create (new prescription for patient), save (meals/foods JSON to existing prescription), publish (release prescription to patient — makes it visible on the patient portal/app).
IMPORTANT: After creating and saving foods, you MUST call publish to make the prescription visible to the patient.

═══ MÉTODO DE PRESCRIÇÃO — escolha no create ═══
WebDiet tem 3 métodos:

• "Convencional" (UI: "Por alimentos", URL: metodoPlanning.php) — DEFAULT e RECOMENDADO. Alimento-por-alimento. Para cálculo de macros automático (proteínas/lipídios/carboidratos/calorias) na tabela "Alimentos prescritos" detalhada, cada alimento DEVE incluir o campo "id" com o WebDiet food-DB ID numérico. Sem id, o alimento AINDA é salvo no método Convencional e aparece no card expandido da refeição com nome + medida caseira, mas sem macros. NÃO vai para a seção qualitativa — o save retorna um warning explicando.

• "Equivalentes"  (UI: "Por equivalentes", URL: metodoWebdiet.php) — avançado. Prescrição por grupos de equivalentes. Requer IDs do banco.

• "Qualitativo"   (UI: "Qualitativa", URL: metodoQualitativo.php) — texto livre por refeição. A página do Qualitativo usa estrutura de dados diferente (refs com objetos cardapio) que este adapter ainda não gera corretamente via save. Para prescrições qualitativas, recomendado: criar via UI ou usar metodo="Convencional" sem food IDs (os alimentos aparecem como texto na refeição sem macros, efeito semelhante).

═══ prescricao_json (para o save) ═══
JSON array de refeições. Cada refeição: {nome, horario, alimentos:[...]}.
Cada alimento: {nome, quantidade, medida_caseira, peso_gramas, id?}.

AUTO-RESOLVE: se "id" não for enviado, o adapter procura automaticamente o melhor match no banco WebDiet (mesmo catálogo do webdiet_food_search) pelo campo "nome" e preenche o id antes de salvar — com isso os macros são calculados mesmo sem pré-chamar webdiet_food_search. O save retorna auto_resolved_foods {resolved, not_found, unresolved[]} indicando quais nomes não tiveram correspondência. Para controle fino (variante específica do banco, gramagem da medida caseira etc.), ainda é recomendado chamar webdiet_food_search e enviar o "id" explicitamente.

Para evitar duplicação na UI ("2 2 fatias (50g)"), use quantidade numérica em "quantidade" e medida_caseira SEM repetir esse número e SEM sufixo "(Xg)" — ex.: quantidade="2", medida_caseira="fatias", peso_gramas="50". O MCP também normaliza automaticamente se você enviar texto completo.

Exemplo sem ids (o adapter resolve automaticamente; nomes pouco específicos podem não encontrar match):
[{"nome":"Café da Manhã","horario":"07:00","alimentos":[{"nome":"Pão integral","quantidade":"2","medida_caseira":"fatias","peso_gramas":"60"}]}]

Exemplo com ids (pula o auto-resolve — ideal quando você já escolheu a variante exata):
[{"nome":"Almoço","horario":"12:00","alimentos":[{"id":"9153","nome":"Arroz branco cozido","quantidade":"4","medida_caseira":"4 colheres de sopa (100g)","peso_gramas":"100"},{"id":"9168","nome":"Feijão carioca cozido","quantidade":"2","medida_caseira":"2 colheres (50g)","peso_gramas":"50"}]}]

O save retorna {ok, metodo, warnings[], raw, auto_resolved_foods}. warnings avisa sobre alimentos sem id e alimentos não encontrados no banco.

[Flattened action: publish]

Bulk support: accepts patient_ids, prescription_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_food_search - Search WebDiet food database for numeric food ids (needed for full macros in Convencional / metodoPlanning prescriptions).
Uses the same data source as the panel (carregarAlimentosAvulsos.php): the full catalog is cached per MCP session and filtered client-side (min 3 characters in keyword, same as the planning UI).
Returns id, nome, grupo, origem, macros (kcal, proteinas, lipidios, carboidratos, fibras), and medidas_caseiras with gram weights. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_orientacoes_list - Read "Listas e Orientações" (guidelines/orientation lists) in WebDiet.
Actions: list (orientation records for a patient), list_banco (orientation bank / favorites — saved templates available to send to any patient).
The orientation bank contains nutritionist's saved/favorite orientations (e.g. "Chás diuréticos", "Refeições livres") that can be sent to any patient. Use list_banco to see available names, then pass those exact names to webdiet_orientacoes_write action=send.

[Flattened action: list]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_orientacoes_list_banco - Read "Listas e Orientações" (guidelines/orientation lists) in WebDiet.
Actions: list (orientation records for a patient), list_banco (orientation bank / favorites — saved templates available to send to any patient).
The orientation bank contains nutritionist's saved/favorite orientations (e.g. "Chás diuréticos", "Refeições livres") that can be sent to any patient. Use list_banco to see available names, then pass those exact names to webdiet_orientacoes_write action=send.

[Flattened action: list_banco]

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_orientacoes_write_save - Create / update / send "Listas e Orientações" in WebDiet.
Actions: save (create/update an orientation for a patient), send (send orientation(s) from the bank to a patient by exact name).
save: non-ASCII emojis in "texto" are encoded as HTML numeric entities so they render on the patient portal (avoids "?" placeholders). If "titulo" is set, an <h1> with the title is prepended to "texto" for the patient view (portal does not show titulo alone).

[Flattened action: save]

Bulk support: accepts patient_ids, orientacao_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_orientacoes_write_send - Create / update / send "Listas e Orientações" in WebDiet.
Actions: save (create/update an orientation for a patient), send (send orientation(s) from the bank to a patient by exact name).
save: non-ASCII emojis in "texto" are encoded as HTML numeric entities so they render on the patient portal (avoids "?" placeholders). If "titulo" is set, an <h1> with the title is prepended to "texto" for the patient view (portal does not show titulo alone).

[Flattened action: send]

Bulk support: accepts patient_ids, orientacao_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_list - Read "Prescrição de manipulados" (compounded/magistral pharmacy formulas) in WebDiet.
Actions:
- list_banco   → search the WebDiet formula bank (~249 pre-built templates: ~120 disponíveis + ~129 de extensões pagas). Filtros: keyword (busca livre na indicação clínica = nome da fórmula), categoria (suplementos | cosmeceuticos | dermatologicos | extensoes), incluir_bloqueados (default false — esconde fórmulas de extensões pagas). Cada item retornado contém: nome (= a indicação clínica), categoria, texto_html (fórmula completa com componentes, doses e modo de usar), bloqueado.
- list         → list manipulados already prescribed to a patient (id, nome, data, liberado, pdf_url + pdf_global_url).
- get          → fetch full HTML content (componentes + doses) of a specific manipulado already prescribed to a patient.

For write operations (save / send / publish / duplicate) use webdiet_manipulados_write.
For destructive delete use webdiet_manipulados_delete.

[Flattened action: list]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_list_banco - Read "Prescrição de manipulados" (compounded/magistral pharmacy formulas) in WebDiet.
Actions:
- list_banco   → search the WebDiet formula bank (~249 pre-built templates: ~120 disponíveis + ~129 de extensões pagas). Filtros: keyword (busca livre na indicação clínica = nome da fórmula), categoria (suplementos | cosmeceuticos | dermatologicos | extensoes), incluir_bloqueados (default false — esconde fórmulas de extensões pagas). Cada item retornado contém: nome (= a indicação clínica), categoria, texto_html (fórmula completa com componentes, doses e modo de usar), bloqueado.
- list         → list manipulados already prescribed to a patient (id, nome, data, liberado, pdf_url + pdf_global_url).
- get          → fetch full HTML content (componentes + doses) of a specific manipulado already prescribed to a patient.

For write operations (save / send / publish / duplicate) use webdiet_manipulados_write.
For destructive delete use webdiet_manipulados_delete.

[Flattened action: list_banco]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_get - Read "Prescrição de manipulados" (compounded/magistral pharmacy formulas) in WebDiet.
Actions:
- list_banco   → search the WebDiet formula bank (~249 pre-built templates: ~120 disponíveis + ~129 de extensões pagas). Filtros: keyword (busca livre na indicação clínica = nome da fórmula), categoria (suplementos | cosmeceuticos | dermatologicos | extensoes), incluir_bloqueados (default false — esconde fórmulas de extensões pagas). Cada item retornado contém: nome (= a indicação clínica), categoria, texto_html (fórmula completa com componentes, doses e modo de usar), bloqueado.
- list         → list manipulados already prescribed to a patient (id, nome, data, liberado, pdf_url + pdf_global_url).
- get          → fetch full HTML content (componentes + doses) of a specific manipulado already prescribed to a patient.

For write operations (save / send / publish / duplicate) use webdiet_manipulados_write.
For destructive delete use webdiet_manipulados_delete.

[Flattened action: get]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_write_save - Create / send / publish / duplicate manipulados in WebDiet.
Actions:
- save       → create or update a manipulado for a patient. texto = raw HTML (tinyMCE content), nome = formula name. Omit manipulado_id to create; pass it to update an existing one. Returns id and pdf_url.
- send       → SHORTCUT prescribir + publicar: copia uma ou mais fórmulas do banco (por nome exato vindo de webdiet_manipulados list_banco) para o paciente como manipulados novos. Já fica liberado=true (visível no app/portal do paciente) imediatamente. Skips fórmulas bloqueadas com mensagem de erro.
- publish    → toggle liberar/disponibilizar status (makes the formula visible/invisible on the patient portal/app). Server toggles and returns the NEW state.
- duplicate  → duplicate an existing manipulado (creates a copy "(cópia)").

For destructive delete use webdiet_manipulados_delete.

[Flattened action: save]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_write_send - Create / send / publish / duplicate manipulados in WebDiet.
Actions:
- save       → create or update a manipulado for a patient. texto = raw HTML (tinyMCE content), nome = formula name. Omit manipulado_id to create; pass it to update an existing one. Returns id and pdf_url.
- send       → SHORTCUT prescribir + publicar: copia uma ou mais fórmulas do banco (por nome exato vindo de webdiet_manipulados list_banco) para o paciente como manipulados novos. Já fica liberado=true (visível no app/portal do paciente) imediatamente. Skips fórmulas bloqueadas com mensagem de erro.
- publish    → toggle liberar/disponibilizar status (makes the formula visible/invisible on the patient portal/app). Server toggles and returns the NEW state.
- duplicate  → duplicate an existing manipulado (creates a copy "(cópia)").

For destructive delete use webdiet_manipulados_delete.

[Flattened action: send]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_write_publish - Create / send / publish / duplicate manipulados in WebDiet.
Actions:
- save       → create or update a manipulado for a patient. texto = raw HTML (tinyMCE content), nome = formula name. Omit manipulado_id to create; pass it to update an existing one. Returns id and pdf_url.
- send       → SHORTCUT prescribir + publicar: copia uma ou mais fórmulas do banco (por nome exato vindo de webdiet_manipulados list_banco) para o paciente como manipulados novos. Já fica liberado=true (visível no app/portal do paciente) imediatamente. Skips fórmulas bloqueadas com mensagem de erro.
- publish    → toggle liberar/disponibilizar status (makes the formula visible/invisible on the patient portal/app). Server toggles and returns the NEW state.
- duplicate  → duplicate an existing manipulado (creates a copy "(cópia)").

For destructive delete use webdiet_manipulados_delete.

[Flattened action: publish]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_write_duplicate - Create / send / publish / duplicate manipulados in WebDiet.
Actions:
- save       → create or update a manipulado for a patient. texto = raw HTML (tinyMCE content), nome = formula name. Omit manipulado_id to create; pass it to update an existing one. Returns id and pdf_url.
- send       → SHORTCUT prescribir + publicar: copia uma ou mais fórmulas do banco (por nome exato vindo de webdiet_manipulados list_banco) para o paciente como manipulados novos. Já fica liberado=true (visível no app/portal do paciente) imediatamente. Skips fórmulas bloqueadas com mensagem de erro.
- publish    → toggle liberar/disponibilizar status (makes the formula visible/invisible on the patient portal/app). Server toggles and returns the NEW state.
- duplicate  → duplicate an existing manipulado (creates a copy "(cópia)").

For destructive delete use webdiet_manipulados_delete.

[Flattened action: duplicate]

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_manipulados_delete - Permanently delete a manipulado for a patient. Irreversible.

Bulk support: accepts patient_ids, manipulado_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_calculo_energetico_list - Read energy expenditure calculations (Cálculo Energético) in WebDiet.
Actions: list (all calculations for a patient), get (load saved data).
Results: TMB (basal metabolic rate), GET (total energy expenditure) in Kcal/dia and Kcal/kg.

[Flattened action: list]

Bulk support: accepts patient_ids, calculo_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_calculo_energetico_get - Read energy expenditure calculations (Cálculo Energético) in WebDiet.
Actions: list (all calculations for a patient), get (load saved data).
Results: TMB (basal metabolic rate), GET (total energy expenditure) in Kcal/dia and Kcal/kg.

[Flattened action: get]

Bulk support: accepts patient_ids, calculo_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_calculo_energetico_write_create - Create / update energy expenditure calculations in WebDiet.
Actions: create (new calculation), save (update existing calculation).
Supports 24+ formulas: Harris-Benedict 1919/1984, FAO/WHO 2004, EER/IOM 2005, EER 2023, Katch-McArdle 1996, Cunningham 1980, Mifflin-St Jeor 1990, and more.
Activity factors: 1.0 (none), 1.2 (sedentary), 1.375 (light), 1.55 (moderate), 1.725 (intense), 1.9 (very intense).
Injury factors: 1.0 (none) up to 2.0 (burns 70-90%).

[Flattened action: create]

Bulk support: accepts patient_ids, calculo_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_calculo_energetico_write_save - Create / update energy expenditure calculations in WebDiet.
Actions: create (new calculation), save (update existing calculation).
Supports 24+ formulas: Harris-Benedict 1919/1984, FAO/WHO 2004, EER/IOM 2005, EER 2023, Katch-McArdle 1996, Cunningham 1980, Mifflin-St Jeor 1990, and more.
Activity factors: 1.0 (none), 1.2 (sedentary), 1.375 (light), 1.55 (moderate), 1.725 (intense), 1.9 (very intense).
Injury factors: 1.0 (none) up to 2.0 (burns 70-90%).

[Flattened action: save]

Bulk support: accepts patient_ids, calculo_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_calculo_energetico_delete - Permanently delete an energy expenditure calculation. Irreversible.

Bulk support: accepts calculo_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_list_anexos - Load educational slides or cloud file attachments. Use laminasAnexos for educational slides/laminas (~238 items with PDFs about nutrition topics), cloudAnexos for uploaded cloud files. For guidelines/orientations specifically, use webdiet_orientacoes action=list_banco.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_get_upload_command - Returns a ready-to-run curl command that uploads a file directly to the server without reading it into context.
RECOMMENDED for large files (images, PDFs, lab results). The flow:
1. Call this tool with the file_path the user provided
2. Execute the returned curl command in your code execution sandbox (or tell the user to run it)
3. The command returns a JSON with a "code" (e.g. "file-a1b2c3d4")
4. Call webdiet_upload_anexo with upload_code=that_code to attach it to the patient
This avoids loading large file contents into the conversation context. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_upload_anexo - Upload a file (PDF, image, etc.) to a patient's attachments in WebDiet.
Three ways to provide the file (use ONE):
  1. upload_code — from webdiet_get_upload_command curl (RECOMMENDED for large files)
  2. file_url — direct URL to download the file (e.g. https://example.com/report.pdf)
  3. file_base64 — base64-encoded file content (small files only)
Supported tipos: anexo (patient attachment — default), cloud (WebDiet Cloud storage), prontuario (clinical record), antropometria (body measurement report), exame (lab exam), perfil (patient photo), evolucao (photo evolution).

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_list_message_templates - Load patient welcome message templates. Returns the active layout and all available template layouts. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_financeiro_list - Read financial records (payments, receipts) in WebDiet.
Actions: list (all records in date range — defaults to last 30 days), categories (get available categories for income/expense).
Each record includes: id, nome, tipo (entrada=income, saida=expense), categoria, valor, data, observacao, recibo status, and recibo_url when receipt was generated.
Use inicio/fim in YYYYMMDDHHmm format to filter by date range (e.g. "202604010000" to "202604302359" for April 2026).

[Flattened action: list] Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_financeiro_categories - Read financial records (payments, receipts) in WebDiet.
Actions: list (all records in date range — defaults to last 30 days), categories (get available categories for income/expense).
Each record includes: id, nome, tipo (entrada=income, saida=expense), categoria, valor, data, observacao, recibo status, and recibo_url when receipt was generated.
Use inicio/fim in YYYYMMDDHHmm format to filter by date range (e.g. "202604010000" to "202604302359" for April 2026).

[Flattened action: categories] Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_financeiro_write - Create financial records in WebDiet.
tipo: "entrada" for income (e.g. consultation payment received), "saida" for expense.
Default income categories: Consulta, Retorno. Default expense categories: Internet, Aluguel. Use nova_cat to create a custom category.
valor format: use comma for decimals (e.g. "300,00" or "150,50"). forma: payment method (e.g. Pix, Dinheiro, Cartão de crédito, Transferência).
parcelas: number of installments (default 1). For installments, dataCobranca is the first billing date.
For destructive delete use webdiet_financeiro_delete.

Bulk support: accepts patient_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_financeiro_delete - Permanently delete a financial record. Irreversible.

Bulk support: accepts financeiro_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- webdiet_recibo - Generate or update a receipt (recibo) for a financial record in WebDiet.
Pass the financeiro_id from webdiet_financeiro list. dados_recibo is a JSON array with 6 fields: [patient_name, cpf, address, city, nutritionist_name, crn_number].
After generating, the recibo_url in the financial record will point to the PDF receipt.
Returns the receipt PDF URL that can be shared with the patient.

Bulk support: accepts financeiro_ids for batched execution. Endpoint: https://api.mcp.ai/p_webdiet
- show_version - Show the current MCP platform and adapter versions. Endpoint: https://api.mcp.ai/p_webdiet
- report_bug - Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction. Endpoint: https://api.mcp.ai/p_webdiet
- connect - Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs. Endpoint: https://api.mcp.ai/p_webdiet
- toolkit_info - Returns the current toolkit state: installed MCPs, their connection status, and how many catalog tools each exposes. Endpoint: https://api.mcp.ai/p_webdiet
- marketplace - The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. Endpoint: https://api.mcp.ai/p_webdiet
- authenticate - MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link. Endpoint: https://api.mcp.ai/p_webdiet

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.mcp-dir
- Version: 0.1.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jun 10, 2026
- Source: https://registry.modelcontextprotocol.io