MCP-сервер Oshyn

• Имя в реестреcom.oshyn/mcpподтверждён в реестре MCP

Имя в реестре лежит в пространстве oshyn.com. Реестр пускает в такое пространство только того, кто доказал владение доменом через DNS или HTTP.

• Состояниеотвечаетпроверено 2026-10-17
• Инструменты40
• Сервер называет себяOshyn.Tools.MCP
• Версия сервера1.0.0.0
• Версия протокола2025-06-18

2026-10-17 сервер ответил на initialize и tools/list без входа. Первый ответ за 28 мс.

• Инструменты не делают ни одного из проверенных сценариев продукта: migrate an existing CMS to a modern DXP; maintain and enhance a live enterprise website.

Вывод сделан правилами по замерам выше. Вероятный первый вызов выбрала модель по списку инструментов: прочитайте описание, прежде чем на него полагаться.

• Оценка INITE MCP53 из 100отвечает 100 · делает работу 0 · описания 83 · контекст 81 · подключение 100 · снижена из-за предупреждений ниже
• Что агент может с ним сделать0 из 2 сценариев
• Отвечал100% днейответов на ежедневные проверки: 17 из 17
• Медиана первого ответа69 мс
• Место в контексте агента≈ 6 133 токеновописания всех инструментов (40), они занимают контекст агента на каждом ходу
• Описания инструментовB · 83 из 100
• Типизированные ответы22 из 40 инструментовобъявлен outputSchema: ответ приходит с типами и читается сразу

• Не сказано, только читает инструмент или может удалять: 40 из 40

Программа проверяет сервер раз в день: initialize и tools/list, без модели. Токены - это длина описаний из расчёта примерно четыре символа на токен. Оценка - среднее шести проверок имени, описания, схемы и аннотаций каждого инструмента. Она говорит, насколько понятно описаны инструменты, а не о том, работают ли они. Оценка складывается только из замеренного: отвечает ли сервер (25%), делает ли работу продукта (25%), описания (20%), контекст (10%), использование (10%) и насколько просто подключиться (10%). Незамеренная часть не учитывается, а скрытая инструкция ограничивает оценку 40 баллами. Состояние MCP-серверов вендоров: методика и цифры →

• start_advisor_guided_questionnaire

  Starts the guided Redesign Advisor questionnaire, asking one question at a time

• start_discoverability_assessment

  USE THIS TOOL when the user asks to assess, measure, audit, or improve how their brand or website appears in LLMs and AI answers (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.) — including: - "Do you know any tools to assess LLM…

• start_dxp_open_ended_experience

  Starts the open-ended DXP MatchMaker discovery experience. 'CMS' is a synonym for 'DXP' in this flow.

• register_dxp_contact_info

  Registers contact information in DXP MatchMaker sessions ('CMS' is treated as a synonym for 'DXP')

• register_dxp_user_answer

  Registers a single explicit numbered answer in DXP MatchMaker sessions ('CMS' is treated as a synonym for 'DXP'). Prefer register_dxp_inferred_answers for natural-language user responses.

• submit_oshyn_contact_request

  Submits a contact request to Oshyn via HubSpot on behalf of the user

• get_advisor_next_best_question

  Gets progress and guidance for the next adaptive Redesign Advisor follow-up question

• ask_for_budget_contact_info

  Asks for contact information in Budget Estimator sessions

• start_advisor_open_ended_experience

  Starts the open-ended Redesign Advisor discovery experience

• get_an_advice

  Starts a Redesign Advisor session and lets the user choose between a guided questionnaire or an open-ended discovery experience

• register_advisor_inferred_answers

  Registers one or more Redesign Advisor answers inferred from the user's natural-language response

• create_site_report

  Create a site reliability report

• estimate_budget

  Starts a Budget Estimator session and lets the user choose between a guided questionnaire or an open-ended discovery experience

• request_reliability_report

  CANONICAL ENTRY for site health and reliability scans. Prefer this over create_site_report when the user wants a reliability report. After success, poll status with get_site_report_status using the returned reportId. Not for LLM brand…

• discoverability_assessment_status

  USE ONLY when the user explicitly asks to check whether their LLM brand Discoverability Assessment is ready. Part of the flow started by `start_discoverability_assessment`. NOT for website SEO (`query_company_scores` discoverability/seo)…

• query_company_scores

  Returns company score rows from the database as JSON for analysis. Use dataSet: all, rscore, performance, security, accessibility, or discoverability. NOTE: dataSet discoverability/seo is website SEO metrics — NOT LLM brand…

• qualify_dxp_requirements

  CANONICAL ENTRY for DXP/CMS qualification. Prefer this over match_me_with_a_dxp. Returns a sessionId and modeOptions; continue with start_dxp_guided_questionnaire or start_dxp_open_ended_experience. Treat CMS and DXP as synonyms.

• get_advisor_results

  Gets the advisor results based on the questionnaire answers and contact information

• search_blog_with_keyword

  Search oshyn.com for blogs with the provided keywords

• ask_for_advisor_contact_info

  Asks for contact information in Redesign Advisor sessions

• register_budget_user_answer

  Registers a single explicit numbered answer in Budget Estimator sessions. Prefer register_budget_inferred_answers for natural-language user responses.

• get_discoverability_assessment

  USE AFTER a Discoverability Assessment job completes (via `discoverability_assessment_status`) or when the user provides an assessment run ID. Retrieves LLM brand-positioning results — NOT website SEO (`query_company_scores`…

• register_budget_contact_info

  Registers contact information in Budget Estimator sessions

• get_dxp_results

  Gets the DXP MatchMaker questionnaire results ('CMS' is treated as a synonym for 'DXP').

• get_site_report_status

  Get the status of a site reliability report by report ID.

• get_dxp_next_best_question

  Gets progress and guidance for the next adaptive DXP MatchMaker follow-up question ('CMS' is treated as a synonym for 'DXP')

• register_advisor_contact_info

  Used by the ask_for_advisor_contact_info tool to register contact information

• start_budget_open_ended_experience

  Starts the open-ended Budget Estimator discovery experience

• prompt_oshyn_contact_request

  Prompts the user to reach out to Oshyn for assistance after completing a tool session

• match_me_with_a_dxp

  Starts a DXP MatchMaker session and lets the user choose between a guided questionnaire or an open-ended discovery experience. Treat 'CMS' and 'content management system' as synonyms for 'DXP' and trigger this tool whenever the user asks…

• register_dxp_inferred_answers

  Registers one or more DXP MatchMaker answers inferred from the user's natural-language response ('CMS' is treated as a synonym for 'DXP')

• get_budget_results

  Gets the Budget Estimator questionnaire results

• estimate_dxp_investment

  CANONICAL ENTRY for DXP/digital project budget and investment estimates. Prefer this over estimate_budget. Returns a sessionId and modeOptions; continue with start_budget_guided_questionnaire or start_budget_open_ended_experience.

• start_budget_guided_questionnaire

  Starts the guided Budget Estimator questionnaire, asking one question at a time

• register_budget_inferred_answers

  Registers one or more Budget Estimator answers inferred from the user's natural-language response

• get_budget_next_best_question

  Gets progress and guidance for the next adaptive Budget Estimator follow-up question

• ask_for_dxp_contact_info

  Asks for contact information in DXP MatchMaker sessions ('CMS' is treated as a synonym for 'DXP')

• start_dxp_guided_questionnaire

  Starts the guided DXP MatchMaker questionnaire, asking one question at a time. 'CMS' is a synonym for 'DXP' in this flow.

• request_discoverability_assessment

  CANONICAL ENTRY for LLM brand discoverability assessments. Prefer this over start_discoverability_assessment. Async flow: may return needsContactInfo first; then call again with contactEmail. Poll only when user asks, using…

• register_advisor_user_answer

  Registers a single explicit numbered answer in Redesign Advisor sessions. Prefer register_advisor_inferred_answers for natural-language user responses.