Summer
Telehealth support for Claude, Codex and Cursor: investigate cases and connect your tools.
使えるツール
summer_github_issues_readCheck issue permission and repository visibility, or read one original GitHub issue by number. Restricted to company-selected repositories; no credentials or writes. Issue closure does not resolve the customer case.summer_github_connection_readRead the company GitHub installation, selected repositories/folders and cached commit status. Makes no GitHub request and returns no credentials.summer_github_connection_startGet the Summer browser URL for a company administrator to install and authorize the Summer GitHub App. Code access is read-only; issue handoffs use separate GitHub Issues permission and exact case approval. Does not grant access or connect an installation by itself.summer_github_repositories_listList repositories available to this company GitHub installation. Provider metadata read; no file content.summer_github_folders_listBrowse repository folders at a branch or commit before selecting access.summer_github_sources_saveChoose repository branches/commits and allowed folders. A dot selects the whole repository. Replaces selections with an expected version and invalidates old cached access. Does not sync code.summer_github_sources_syncRefresh the selected repository code cache once from GitHub. Reuses the cache for an unchanged commit; sandbox startup never pulls GitHub.summer_github_sources_readList cached source paths, or read one cached file with path. Only currently selected company folders are available. No live GitHub call or credentials.summer_github_connection_disconnectDisconnect this company/environment GitHub source access and remove its cached archives.summer_reports_themes_getRead one saved recurring-issue report and its source snapshot, including reports older than the latest list. Requires current operational company access.summer_reports_themes_listRead the latest private recurring-issue reports, original case references, source coverage, generation status and human review. Generated themes are suggestions, not verified causes.summer_reports_themes_generateGenerate a private recurring-issue report from the admitted case-summary cohort. One immutable request ID prevents duplicate inference. No customer, knowledge or publication effect.summer_reports_themes_reviewRecord a human disposition on a saved recurring-issue theme at its expected revision. Retains the original analysis and source references; does not change cases or company knowledge.summer_workflows_listRead built-in tasks and company/environment-owned workflow templates. Selecting one never runs work.summer_workflows_historyRead the original revisions and authenticated edits for a saved workflow.summer_workflows_saveSave, retire or restore a task template with its expected revision. Changes no case or effect authority.summer_workflows_request_textPrepare editable operator guidance from an exact active workflow revision and feedback. Starts no investigation and executes no action.summer_support_policy_readRead business hours, holidays, response commitments and scheduled policy revisions.summer_support_policy_updateSave business hours and response commitments with the expected revision and an effective date.summer_saved_replies_listRead company saved replies, optionally including retired replies.summer_saved_replies_saveCreate, edit, retire or restore a saved reply with its expected revision and reason. Sends nothing. API reference: https://api.gosummer.ai/v1/openapi.jsonsummer_saved_replies_historyRead original revisions of a saved reply.summer_saved_views_listRead this person's saved inbox views and shared company views.summer_saved_views_saveSave a personal or shared inbox view. Known case filters are normalized by the same service as the UI.summer_saved_views_deleteRemove an owned inbox view, retaining the database's ownership checks.summer_quality_scenarios_listRead quality scenarios, assessments and current outcomes.summer_quality_scenarios_getRead one scenario and its saved assessments.summer_quality_scenarios_saveCreate, revise or retire a quality scenario, with expected revision and reason.summer_quality_assessments_saveRecord an evidence-backed assessment or correction. Does not approve a plan or customer action.summer_quality_corrections_listRead evidence-backed corrections to previous quality assessments.summer_privacy_requests_listRead privacy export/deletion requests, status and original event history. Does not export or delete data.summer_privacy_requests_createFile an export or deletion request for human review. Cannot approve, perform or attest completion of the work.summer_work_routing_readRead eligible teammates and automatic routing for new issues, plan reviews and human tasks.summer_work_routing_updateSave automatic routing for new issues, plan reviews and human tasks with the expected version. Does not grant roles or approval authority.summer_router_rules_readRead the rules Summer applies before any agent runs, in plain words, with this week's decisions and how often each rule matched. Routing costs no model call.summer_router_rules_updateSave the router rules with the expected version and a reason. Keeps the original revision and updates the Routing rules knowledge document. Run router_rules.test first. Needs a company admin.summer_router_rules_testCheck proposed router rules without saving: lists rule problems, replays recorded ticket activity under the saved and the proposed rules, and routes optional sample facts. Changes nothing.summer_router_rules_historyRead every saved revision of the router rules, with who changed them and why.summer_router_rules_decisionsRead what the router decided and why: totals by outcome, day and rule for the last 7, 30 or 90 days, and pages of decisions with a short plain reason each and the case. Changes nothing.summer_cases_engineering_listRead private engineering issue associations, optionally checking original GitHub state. Does not close cases or send replies.summer_cases_similar_listRead bounded original case-summary text matches, with source observation and matching terms. Does not establish customer identity, link cases, call a model or start work.summer_slack_discussions_channelsRead connected Slack posting channels, or inspect the current internal channel name/privacy, posting revision and authenticated sender. Enables no grant and posts nothing.summer_cases_discussions_readRead original Slack replies for an exact recorded case discussion. A root supplied for an unknown send must match the saved original sender, approved text and operation metadata before its source can be retained. Never posts or approves work.summer_cases_discussions_listRead case-linked Slack discussion receipts and original thread links. Unknown posting stays unknown; no message is sent.summer_cases_queued_texts_listRead the approved plans' texts on this customer's ticket that are waiting for the customer's texting hours (8am to 9pm their time): each text's exact words, a masked phone, when it sends (sends_at and a plain label such as Sends at 8:00 AM PDT) and its source (quo: a direct text from the case; summer: a reply in a Summer texting conversation). Lists only texts still waiting. Changes nothing.summer_cases_queued_texts_cancelCancel one approved plan's text while it waits for the customer's texting hours. It is never sent; Summer records who cancelled it and adds a case activity entry. A text that is sending, sent or has an unknown result cannot be cancelled and keeps its state. The rest of the plan is unchanged and nothing is sent.summer_cases_assignment_readRead a case's issue owner, plan reviewer and eligible teammates.summer_cases_assignment_updateAssign an issue owner or plan reviewer with the previous owner as a conflict check. Does not grant roles or approve a plan.summer_reports_creditsRead all-time and month-to-date credits, pending reservations and monthly usage in the company timezone. Phone calls use the phone kind and add call counts, answered seconds and calls whose cost is not fully known. Carrier minutes are not included.summer_reports_ticket_activityRead tickets opened and closed over 1, 7 or 30 company-local calendar days or all recorded history. Includes zero-filled hourly, daily or monthly bars, period totals, open tickets now and closures without usable dates. backlog contains from, historyEstimated and bounded points (at, open) for open issues over time, reconstructed from creation and latest valid closure dates. Past reopen cycles and resolved issues without dates cannot be reconstructed. The final backlog point equals openNow. Read-only Intercom archives are excluded from operational issues, messages and closures in ticket activity, service metrics and samples; coverage.archivedImports gives their count. Original archives are retained unchanged. rolling contains a dense series of original-timestamp trailing counts with windowSeconds, stepSeconds, from and points (at, opened, closed). Windows are one hour for 1d, 24 hours for 7d/30d, and 24 hours, 7 days, 30 days or 365 days for all-time depending on history length. At most 722 points include the exact observation time; lookback before the selected period is included in rolling counts, while period totals remain exact calendar counts. Reopened tickets are open; a completed run is not a closure. Changes nothing.summer_reports_samples_listRead paginated original issue/message references behind service counts and timing samples, with date/channel/hour filters in the company timezone. Read-only Intercom archive projections are excluded from operational workload counts. No messages are sent or marked read.summer_reports_service_metricsRead response and resolution metrics, 90-day daily issue/message and timing trends, and weekday/hour incoming-message heatmaps in the company timezone. Read-only Intercom archive projections are excluded from operational workload counts. Missing timings stay unmeasured. fullyAutomatic counts original automatic-plan and routine-rule issue closures, including linked issues; earlier human help and pending run verification do not make the closure manual. closedWithoutPerson is the strict subset where no person approved or edited a plan, replied, finished a human task or changed the case on the issue or a linked issue before it closed. automationByCategory and automationByChannel break resolved, fullyAutomatic and closedWithoutPerson down by case category and channel; daily trends include both closure counts.summer_reports_autonomy_funnelRead daily counts for each stage of Summer's work, in the company timezone: router decisions by route, investigations started, completed and cancelled, plans published and replaced before anyone acted, auto-run decisions with their reasons, approvals by a person, an agent or auto-run, approved runs by status (previews nobody approved are not counted), executed plans with a checked result, and issues resolved, closed automatically and closed without a person. Counts are recorded events, not verified customer outcomes. Starts no work.summer_reports_autonomy_calibrationRead how well Summer's own "run it" call matches what happened, per action and per action family (reply, closure, record, vendor_contact, clinician_note, address_cancel, money, other) over the last 14 and 30 days: plans proposing it, the agent's calls, what people did (approved unchanged, with direction, edited, another option, dismissed, superseded), auto-run decisions with each action's reason and deciding rule, the action's run results (completed, failed, unknown), checked results, daily closure audit verdicts and corrected quality assessments on those tickets. Each family and action has an error rate (person changes to plans the agent said to run, failed or unknown runs and failed audits, over decided plans) and a status: ready_to_widen (at least 30 decisions and under 1% errors in 14 days), keep, or tighten (over 5%). Families show the saved policy's kill switch or automatic rule. Categories show closed-without-a-person and audited-correct rates against the 95% and 98% targets, with the gap. Counts are recorded events, not verified customer outcomes. Calls no model and starts no work.summer_reports_agent_timingRead how long approved agent runs take: approval to start, each startup and work phase, and each step by action and category, with medians, 90th percentiles and recent runs. Phases that were not recorded stay unmeasured. Starts no work.summer_reports_cancellationsRead cancellation requests and how each ended: paused, renewal moved later, kept, cancelled, or a pause offered with no answer yet. The investigating agent marks each request; the approved plan option sets the outcome. revenue:true adds each saved plan's renewal amount and the paid renewals collected since the save (before refunds), read from live billing, plus gross totals. Changes nothing.summer_reports_deliveryRead delivery attempts, failures and recorded results. Does not retry a delivery.summer_delivery_bulkAct on several rows from reports.delivery at once: request a new plan, approve each case's current saved plan and run it, or start an approved plan that is waiting. Returns done, skipped or failed with a reason for each row. Rows with no confirmed result are never run again. Approval binds to each case's exact saved plan and prepared changes; plans that changed or need a choice between options are skipped. request_plan needs investigations.request; the others need a person's delegated actions.approve.summer_reports_commitmentsRead outstanding customer promises and unfinished work.summer_human_tasks_listRead work that Summer agents or blocked approvals asked a person to do, with owners, due times, recorded outcomes and change history for one selected task.
Claude / Cursor への設定
{
"mcpServers": {
"remote-ai-gosummer-summer": {
"type": "http",
"url": "https://api.gosummer.ai/mcp"
}
}
}出典
- 更新日:2026-10-29
同じ分類の他の MCP
资料来自官方仓库与 MCP 接口探测,以官方最新文档为准;安装第三方 MCP server 前请自行评估安全风险。