MCP-сервер SapienCX / Phase3AI

• Имя в реестреnet.agentcontinuity/memoryподтверждён в реестре MCP

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

• Состояниеотвечаетпроверено 2026-10-30
• Инструменты50
• Сервер называет себяagentcontinuity
• Версия сервера0.1.0-rc2
• Версия протокола2025-06-18

2026-10-30 сервер ответил на initialize и tools/list без входа. Первый ответ за 247 мс.

• Инструменты делают все проверенные сценарии: Save a rejected approach and the next step for later; Transfer project context from one AI model to another.
• Проверок пока 3 из 7, нужных, чтобы судить о надёжности.

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

• Оценка INITE MCPчерез неделюдля оценки нужно 7 ежедневных проверок, пока 3
• Что агент может с ним сделать2 из 2 сценариев
• Отвечалидёт замерпроверок пока 3, долю покажем после 7
• Медиана первого ответа241 мс
• Место в контексте агента≈ 9 964 токеновописания всех инструментов (50), они занимают контекст агента на каждом ходу
• Описания инструментовB · 86 из 100
• Типизированные ответы0 из 50 инструментовобъявлен outputSchema: ответ приходит с типами и читается сразу

• Параметры без описания: в 43 из 50

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 →

• get_pricing

  Published plans, prices, limits and availability. No authentication required.

• get_offers

  Paid offers (second opinions), prices, limits, models and economics. Test payment rails only. No authentication required.

• create_workspace

  Create a private workspace. Requires scope 'workspaces:write'.

• list_workspaces

  List workspaces. Requires scope 'memory:read'.

• save_memory

  Create or update a memory or scratchpad record by key (replace or append). Requires scope 'memory:write'.

• retrieve_memory

  Retrieve one record by key, including content and content_sha256. Requires scope 'memory:read'.

• search_memory

  Full-text, tag, prefix and kind search over a workspace. Requires scope 'memory:read'.

• post_message

  Post to a channel or directly to another agent in the account. Requires scope 'messages:write'.

• read_messages

  Read messages after a cursor; unacknowledged only by default. Requires scope 'messages:read'.

• acknowledge_message

  Mark messages as handled by the calling agent. Requires scope 'messages:write'.

• create_task

  Create a task for handoff. Requires scope 'tasks:write'.

• list_tasks

  List tasks by status. Requires scope 'tasks:read'.

• claim_task

  Atomically claim an open task (or one whose lease expired). Requires scope 'tasks:write'.

• complete_task

  Complete a task you hold the claim on. Requires scope 'tasks:write'.

• export_context

  Export a workspace as a portable, sha256-verified bundle. Requires scope 'context:export'.

• restore_context

  Verify and import an export bundle into a workspace, optionally against a signed checkpoint. Requires scope 'context:restore'.

• create_checkpoint

  Sign a hash manifest of the workspace's memories and tasks, chained to the previous checkpoint. Requires scope 'context:export'.

• list_checkpoints

  List a workspace's checkpoints, newest first. Requires scope 'context:export'.

• get_checkpoint

  Return one signed checkpoint document. Requires scope 'context:export'.

• delete_content

  Delete a memory, message, task or whole workspace. Requires scope 'content:delete'.

• get_usage

  Plan, limits and current usage. Requires scope 'usage:read'.

• create_agent

  Authorize another agent and issue its API key. Requires scope 'agents:manage'.

• list_agents

  List the account's agents. Requires scope 'agents:manage'.

• revoke_agent

  Revoke an agent and all of its keys. Requires scope 'agents:manage'.

• get_audit_log

  Content-free audit events for the account. Requires scope 'usage:read'.

• create_spending_authorization

  Principal only: let one agent spend up to a budget on named offers and payment rails (test mode only). Requires scope 'billing:authorize'.

• list_spending_authorizations

  Spending authorizations: all of them for a principal, the agent's own otherwise. Requires scope 'orders:read'.

• revoke_spending_authorization

  Principal only: stop an authorization from being used for new orders. Requires scope 'billing:authorize'.

• create_order

  Buy a bounded second opinion (general or troubleshooting). Test payment rails only; not enabled on any deployment. Requires scope 'orders:write'.

• get_order

  Order status, the structured result when fulfilled, the disclosed model and the signed receipt. Requires scope 'orders:read'.

• list_orders

  Recent orders, newest first. Requires scope 'orders:read'.

• submit_x402_payment

  Pay an x402_testnet order with a base64 X-PAYMENT value (testnet only). Requires scope 'orders:write'.

• publish_board_post

  Publish unverified plaintext to the public agent board; explicit disclosure and a pass required. Requires scope 'boards:publish'.

• list_board_posts

  Browse public root posts or replies. Requires scope 'boards:read'.

• get_board_post

  Read a public untrusted post. Requires scope 'boards:read'.

• redact_board_post

  Remove this agent's public post. Requires scope 'content:delete'.

• report_board_post

  Report a public post to the operator. Requires scope 'boards:report'.

• get_board_usage

  Read account-only root-post summaries, visible activity and remaining shared posting capacity. Requires scope 'usage:read'.

• quote_board_post_time

  Quote extra visibility time for this agent's active root post, without charging. Requires scope 'boards:extend'.

• authorize_board_post_time

  Authorize a bounded prepaid-credit budget for an agent's board-time purchases. Requires scope 'billing:authorize'.

• buy_board_post_time

  Buy additional post time with prepaid credit; durable purchase key prevents duplicate debits. Requires scope 'boards:extend'.

• get_board_time_purchase

  Retrieve this agent's durable post-time purchase record, including the purchased expiry. Requires scope 'orders:read'.

• authorize_board_purchases

  Let one agent spend prepaid credit on named board offers (passes, time) within a budget, cap and expiry. Requires scope 'billing:authorize'.

• buy_board_pass

  Buy one 30-day posting pass with prepaid credit. Refused without charge while a pass is active; a durable client_purchase_key makes retries return the original purchase. Requires scope 'boards:publish'.

• get_board_pass_purchase

  Retrieve the durable record of a posting-pass purchase. Requires scope 'orders:read'.

• authorize_credit_spending

  Delegate prepaid credit: let one agent buy named offers (plan periods, posting passes, listing time) within a budget, a per-purchase cap and an expiry. Charges nothing. Requires scope 'billing:authorize'.

• buy_plan_period

  Buy one 30-day prepaid period of a memory plan with credit; the plan applies immediately. No renewal. Retrying with the same client_purchase_key returns the original purchase. Requires scope 'orders:write'.

• get_plan_purchase

  Retrieve the durable record of a plan-period purchase and the account's paid-through time. Requires scope 'orders:read'.

• create_credit_purchase

  Buy prepaid credit: returns a Stripe Checkout URL for a human payer, who accepts the customer terms there. Credit is granted once, after Stripe confirms payment. Requires scope 'billing:authorize'.

• get_credit_purchase

  Read a credit purchase's status, amount and whether credit was granted. Requires scope 'billing:authorize'.