This was a duplicate manual listing. Use Summer’s official listing, imported from the official MCP Registry. Summer’s MCP server remains active at https://api.gosummer.ai/mcp. Setup and documentation: https://gosummer.ai/docs/mcp-clients.
Connect AI agents to Summer to set up and manage telehealth support and operations. Uses OAuth 2.1 and scoped company access; setup and API documentation are at https://gosummer.ai/docs/agent-setup.
Scored across 235 tools
With 235 tools, many domains expose adjacent read/list/update operations (e.g., cases, investigations, runs, plans, reports, Slack, and knowledge), so an agent may hesitate between similar resources. Descriptions are detailed and often clarify scope, but the sheer volume and crossed concepts like queued messages versus case queues create real overlap.
All tool names use snake_case and follow a broadly consistent summer_<domain>_<object>_<action> pattern, with actions usually at the end. Minor deviations like summer_account_me or summer_cases_account are still readable and clearly grouped.
235 tools is far beyond the 3–15 well-scoped range and well past the 50+ threshold for extreme mismatch. Even for a large platform, this surface is excessive and imposes a heavy tool-selection burden.
The surface covers a vast range of lifecycle operations—read, list, create, update, save, publish, retire, test, preview—across cases, knowledge, guides, Slack, reports, and more. Some gaps exist (e.g., no direct case creation/deletion, limited approval-side operations), but core workflows are broadly covered.
Read the person's Summer access request. Approval is a separate Summer team decision.
Inputs: no named parameters.
Submit or update a Summer access request. This cannot approve access.
Inputs: note (required), company_name (required), idempotency_key.
List companies the person can access and whether this connection includes each one.
Inputs: no named parameters.
List this person's agent connections, grants, last use and expiry.
Inputs: no named parameters.
Revoke one of this person's agent connections immediately.
Inputs: connection (required), reason, idempotency_key.
Show the signed-in person, Summer access status, profile photo path and this connection's grant.
Inputs: no named parameters.
Remove your own profile photo. Replies you send afterward show your initials; earlier replies keep the photo they were sent with.
Inputs: idempotency_key.
Approve the exact prepared execution under the authenticated operator's delegated authority. Use only for work the operator authorized, read the prepared review first, and pass its exact hash. Records the authorization and queues ordinary execution; approval does not prove a customer outcome. No caller-supplied approver identity or identity-verification attestation.
Inputs: case (required), company (required), execution (required), environment (required), +3 more.
List approved work from the last 60 days that no catalogue action covers: free-form tasks and raw API calls, with how often each recurred. Each can become a company action with actions.company.from_run. Changes nothing.
Inputs: company (required), environment (required).
List every action Summer can use for this company, the hosts each saved credential may be sent to, and the partner contacts the company named: built-in actions, connector actions and the company's own actions. Each shows its stage (off, review or automatic), whether it can ever run without a person, and its track record over 30 days: proposals, unchanged approvals, runs, uncertain runs and runs without a person. Changes nothing.
Inputs: company (required), environment (required).
Save one piece of approved work as a draft company action: the task's instructions, or the API call's method, path and body (give its https origin). Replace case details with inputs, test and publish it like any other action. Never publishes.
Inputs: key (required), job_id (required), company (required), environment (required), +4 more.
Read one company action: its draft, published revision, revision history, stage and stage history.
Inputs: key (required), company (required), environment (required).
Publish the current draft as the next revision with the expected version. The agent can propose it from the next investigation. A new action starts at Review: a person approves each use until an admin moves it to Automatic.
Inputs: key (required), reason (required), company (required), environment (required), +2 more.
Remove a company action from the agent's catalogue with the expected version. Approved work that uses it stops before it starts. Revisions and history stay.
Inputs: key (required), reason (required), company (required), environment (required), +2 more.
Create or edit a company action's draft with the expected version. An API action (runner http) names the request Summer sends: method, https host, path, body and the saved credential name. A task action (runner agent) describes work the agent does with its own tools, such as a procedure or a website task. The agent sees only published revisions. Saving never publishes.
Inputs: key (required), company (required), definition (required), environment (required), +2 more.
Render the draft or published action with example inputs: the exact request (without the credential) or the exact task text, plus any problems. Sends nothing and changes nothing.
Inputs: key (required), company (required), environment (required), use, +1 more.
Prepare the exact current plan and return its execution ID, approval hash and reviewed work. Does not approve or execute. A delegated actions.approve grant can approve authorized work through API, CLI or MCP.
Inputs: case (required), company (required), environment (required), plan_request_id (required), +2 more.
Try a saved plan approval again when it is waiting to start (its id is in investigations.list planApprovals). Returns the approval's current state and the reason when it still cannot start. start_anyway ends the case's stopped runs that have no checked result, recording this person, so the approved plan starts; an earlier run may already have made its changes. A run still working keeps blocking.
Inputs: case (required), company (required), approval (required), environment (required), +3 more.
Set one action's stage with the expected version: off (never proposed), review (a person approves each use) or automatic (may run without a person when the company policy and the agent's checks allow). Automatic needs a person's delegated messaging.activate grant. A task action at automatic also needs described_accepted: true. Money, identity, clinical and other person-only actions cannot be automatic. A failed or uncertain automatic run moves the action back to review on its own.
Inputs: key (required), stage (required), reason (required), company (required), +5 more.
Read the company's sender exclusions and original edit history. Changes retain human approval.
Inputs: company (required), environment (required).
Edit guide media captions, alt text, provenance, transcript or poster at the expected version, or retire unused media. Published releases keep their pinned metadata.
Inputs: asset (required), reason (required), caption (required), company (required), +7 more.
Read one guide asset, checksum and resumable chunk receipts. No secret upload capability is returned.
Inputs: asset (required), company (required).
List the company's private guide media, metadata and upload status. Uploading does not make a file public.
Inputs: company (required).
Verify the original size, content signature and SHA-256 against saved private bytes, then mark a guide upload ready. A ready file remains private until published in a guide.
Inputs: asset (required), company (required), idempotency_key.
Start or recover a private resumable Markdown, image, video, PDF or caption upload from metadata. File bytes are transferred separately; this hosted endpoint has no local filesystem access.
Inputs: id (required), sha256 (required), caption (required), company (required), +8 more.
Count latest pending plans per open ticket across the connected operations company, including partner/system/operator origins. Other tenants cover only their Messenger tickets. Returns aggregate scores, holds, coverage and an exact refresh preview; starts nothing. auto_run:true previews only plans that could run on their own under current auto-run settings.
Inputs: company (required), environment (required), auto_run, missing_only.
Queue fresh research for the exact pending-plan preview, up to 100 tickets. Each fresh plan follows the ordinary auto-run eligibility rule. auto_run:true (matching the preview) picks only plans that could run on their own. Never replays old effects. Requires a new preview if work changed; successful repeats return the original receipt.
Inputs: company (required), environment (required), preview_hash (required), auto_run, +2 more.
Draft one action family's change to the saved company execution policy and preview it. widen adds an automatic rule for a family that reports.autonomy_calibration marks ready_to_widen: at least 30 decided plans and under 1% errors in 14 days. hold adds the family's kill switch: a review rule with threshold 100 that holds every action in the family whatever the other rules say. Returns the drafted settings, the expected version and the autonomy.policy.preview result with its preview_hash. Saves nothing; a person publishes the change with autonomy.policy.update. Money stays within the policy's money limits, and Slack posts still wait unless a rule names Slack.
Inputs: family (required), company (required), environment (required), change, +1 more.
Preview the complete replacement execution policy. Conversation reply grants remain separate; explicit communication review exceptions apply to replies too. Optional partial (run the leading qualifying steps, leave the rest with a person) is off when omitted. Money limits (refund, credit and daily totals in cents) default to $200 per refund, $100 per credit and $500 in 24 hours when omitted. Returns an exact preview hash; changes nothing.
Inputs: company (required), version (required), settings (required), environment (required).
Publish the complete previewed company execution policy under the authenticated administrator's authority. Requires a person's delegated messaging.activate grant, expected version and preview_hash. Replaces legacy inbound-channel plan permission. Does not run old held plans.
Inputs: company (required), version (required), settings (required), environment (required), +2 more.
Read one capability, its concrete test, evidence and latest 20 review records.
Inputs: company (required), capability (required), environment (required).
Read the same operational capability checklist, results, discovery paths and review history shown in Summer. Every usable API, browser or knowledge path can count.
Inputs: company (required), environment (required).
Record the setup agent's capability assessment with original evidence and the path Summer can discover and use. A pass needs evidence and a discovery path. Reports are labeled as agent-reported, never human approval or independently verified execution.
Inputs: notes (required), state (required), company (required), evidence (required), +5 more.
Edit a capability expectation or add a business-specific custom_ capability with a reason. Resets its result and retains history. Does not create a provider tool or grant execution access.
Inputs: notes (required), company (required), capability (required), definition (required), +3 more.
Request a read-only Summer capability test on an authorized sample case. Also needs investigations.request and current runtime access. Does not approve or execute customer changes.
Inputs: case_id (required), company (required), capability (required), environment (required), +2 more.
Read the case customer's subscriptions and upcoming shipments, the same account facts used by the chat agent and Details panel: renewal and next-charge dates, recurring price/currency, pauses and scheduled ends, refill due dates and prepaid fills, fulfillment and tracking. Planned dates are not confirmed ship dates. Read coverage distinguishes unknown from absent; no customer changes are made.
Inputs: case (required), company (required), environment (required).
Read a case's issue owner, plan reviewer and eligible teammates.
Inputs: case (required), company (required), environment (required).
Assign an issue owner or plan reviewer with the previous owner as a conflict check. Does not grant roles or approve a plan.
Inputs: case (required), company (required), memberId (required), previous (required), +3 more.
Get a short-lived download for an attachment that belongs to this case.
Inputs: case (required), company (required), attachment (required), environment (required).
Read an original care-message attachment as name, content_type, size_bytes and data_base64 (up to 20 MiB). Use careMessageId and preview.attachments index from cases.get. Checks the case customer, message owner and environment on every read.
Inputs: case (required), index (required), company (required), message (required), +1 more.
Ask Summer a question about the case, such as why it chose a plan or what it found. Summer reopens its last run on the case, with what it already read, and answers in the case chat. Read-only: it publishes no plan and makes no changes. One question at a time per case. Read cases.chat.list for the answer, which usually takes a minute or two. To change the plan, use investigations.request.
Inputs: case (required), company (required), question (required), environment (required), +1 more.
Read the case chat with Summer: each question people asked about the case, oldest first, with its status and Summer's saved answer (the latest 10). An answer is Summer's explanation of its own work, not new evidence, approval or a customer outcome.
Inputs: case (required), company (required), environment (required).
Read the case customer's profile: name, date of birth, contact details, default shipping and billing addresses, each order's addresses and earlier addresses. A saved address does not prove where an existing order ships.
Inputs: case (required), company (required), environment (required).
Read case-linked Slack discussion receipts and original thread links. Unknown posting stays unknown; no message is sent.
Inputs: case (required), company (required), environment (required).
Read 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.
Inputs: case (required), company (required), operation (required), environment (required), +2 more.
Read private engineering issue associations, optionally checking original GitHub state. Does not close cases or send replies.
Inputs: case (required), company (required), environment (required), refresh.
Read one case or conversation with its original messages and related records. Operational records include workspace with the current customer ticket and all owned issue references, plus the shared saved timeline, including original inbound phone transcripts, caller-supplied pharmacy intake and private tool receipts with attempts and results. Generated speech is not proof the caller heard it; saved intake is not resolution. The conversation field includes messages, other_threads and activity from the same case feed: original email From/To headers, Slack sender/channel, and care routing audience/direction/endpoints when recorded. Missing headers stay unknown; routing is display evidence, never reply authorization. The original case identity is retained. Includes conversationSentiment with happy, neutral, upset, angry, sad, mixed or unknown, confidence, exact evidence references, source, assessed_at and pending freshness; an estimate does not prove resolution. contact_sources lists each name, email and phone with its source (account, staff-saved or the website chat form) and a plain note; chat form details are self-reported, never identity proof or a reply address. Each customer_records.orders item has supply: paid plan months, each product's package days, the newest prescriptions with quantity, refills and days per fill (with its source), the shipment sequence of a split plan and a plain summary; unavailable:true means unknown, not none. Supply facts never give dosing.
Inputs: case (required), company (required), environment (required), after.
List company-owned cases or conversations with emotion filters (sentiment: happy, neutral, upset, angry, sad, mixed or unknown), a customer filter (customer: paid for a captured or authorized live payment, no_purchase for a matched contact who has not paid, unmatched for an unknown sender), ordering (sort, including customer_message for the latest customer message first), page size, coverage and a cursor. Operational rows include conversationSentiment (label, confidence, evidence references, source, assessed_at and pending freshness). Operational filters require the company's operational connection; Messenger-only results include coverage limits.
Inputs: company (required), environment (required), lane, mine, +23 more.
Cancel an exact queued Slack message before it starts sending. Sending, sent and uncertain messages cannot be cancelled. Records the authenticated operator and changes no other plan step.
Inputs: case (required), company (required), message (required), environment (required), +1 more.
Read Slack messages queued for office hours on this exact case, their approved words, destination, scheduled opening and delivery result. Changes nothing.
Inputs: case (required), company (required), environment (required).
Cancel 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.
Inputs: case (required), text (required), source (required), company (required), +2 more.
Read 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.
Inputs: case (required), company (required), environment (required).
Find cases by customer name, email, phone, date of birth, support code, order or tracking number, vendor or Stripe ID, or message words, with status and date filters. Returns one current workspace per verified customer (explicit splits stay separate), with the actual ticket code, all issue references, plan and run progress, orders and message excerpts. Message case_id opens the workspace; source_case_id retains the original issue. Search matches are leads, not proof of identity or completed work.
Inputs: company (required), environment (required), q, dob, +8 more.
Read 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.
Inputs: case (required), company (required), environment (required), limit.
Prepare reusable company knowledge from an operator correction or human reply and a fast reply draft from the saved conversation. Also requires cases.read. Saves and sends nothing; no investigation is queued.
Inputs: case (required), text (required), source (required), company (required), +2 more.
Save the exact reviewed reusable fact in shared company core guidance at the expected revision, with original operator text and case provenance. Also requires cases.read and current company and Ops admin rights. Does not send the reply or restart an agent.
Inputs: case (required), text (required), title (required), source (required), +6 more.
Check live Summer MCP/API versions, old client warnings and the seven-day discovery refresh interval. Optional cached client versions and the last successful check timestamp distinguish known and unknown status.
Inputs: cli_version, mcp_version, last_checked_at.
What this connection can do here, with a reason for everything unavailable.
Inputs: company (required), environment (required).
Read company-wide settings, including the email subject customers see on new support emails. Changes affect every environment.
Inputs: company (required).
Update company-wide settings with the expected version. Affects every environment.
Inputs: name (required), note (required), company (required), timezone (required), +4 more.
Saved, verified, pending, unavailable and enabled state for each setup item.
Inputs: company (required), environment (required).
List company members and pending invitations. Role changes and invitations stay in Summer.
Inputs: company (required).
List saved credential names, sources and versions. Never returns values.
Inputs: company (required), environment (required).
Set the hosts company actions may send one saved credential to, with the expected version (0 when it has no scope yet). Use exact https hosts, or https://*.example.com for any subdomain. A key with no scope may be sent to any public https host. Never reads or changes the value.
Inputs: name (required), hosts (required), reason (required), company (required), +3 more.
Save one selected credential value or Doppler reference. Replacing an active credential needs credentials.replace. Returns metadata only. Returns a local CLI command when a secret is involved.
Inputs: name (required), source (required), company (required), environment (required), +3 more.
Save an owned administrative customer and contact discovery leads with source evidence at an expected revision. Optionally associate a sourced Bask providerPatient ID atomically. Company admin required. Retains history; never verifies a patient, links a sign-in session, enables a provider or authorizes a customer effect.
Inputs: id (required), company (required), contacts (required), displayName (required), +5 more.
Search the saved company customer store by name, customer UUID, provider identifier or exact email/E.164 phone. Returns separate ambiguous candidates, source evidence and honest coverage. Discovery never verifies account access or searches Rebody Auth.
Inputs: q (required), company (required), environment (required).
Act 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.
Inputs: action (required), company (required), attempts (required), environment (required), +2 more.
Read configuration and activity events after a cursor. Pagination uses next_cursor.
Inputs: company (required), environment (required), after, limit.
Disconnect this company/environment GitHub source access and remove its cached archives.
Inputs: company (required), environment (required), expected_version (required), idempotency_key.
Read the company GitHub installation, selected repositories/folders and cached commit status. Makes no GitHub request and returns no credentials.
Inputs: company (required), environment (required).
Get 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.
Inputs: company (required), environment (required).
Browse repository folders at a branch or commit before selecting access.
Inputs: ref (required), company (required), repository (required), environment (required), +2 more.
Check 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.
Inputs: company (required), source_id (required), environment (required), number.
List repositories available to this company GitHub installation. Provider metadata read; no file content.
Inputs: company (required), environment (required), page.
List cached source paths, or read one cached file with path. Only currently selected company folders are available. No live GitHub call or credentials.
Inputs: company (required), source_id (required), environment (required), path, +1 more.
Choose 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.
Inputs: company (required), sources (required), environment (required), expected_version (required), +1 more.
Refresh the selected repository code cache once from GitHub. Reuses the cache for an unchanged commit; sandbox startup never pulls GitHub.
Inputs: company (required), source_id (required), environment (required), idempotency_key.
Read an editable guide article and its current knowledge revision.
Inputs: article (required), company (required).
Create or edit a Markdown customer article with source references and managed asset IDs. Saves a draft in the shared knowledge library; later edits do not change a published release.
Inputs: slug (required), title (required), topic (required), reason (required), +9 more.
Read the company's reviewed guide-authoring brief, draft article references and publication state. This read starts no model run and changes no customer data.
Inputs: company (required).
Read the company's editable guidebook, draft articles, assets and publication state. Customer guides share the existing company knowledge source.
Inputs: company (required).
Read the company's guide edits, upload and publication history.
Inputs: company (required).
Read the optional custom guide domain, DNS instructions and verified HTTPS status. Summer-hosted guide URLs need no customer DNS setup.
Inputs: company (required).
Save or remove a custom guide hostname at the expected version. Saving a name does not verify ownership or provision HTTPS.
Inputs: company (required), hostname (required), expected_version (required), idempotency_key.
Check the saved domain's DNS ownership, attach it through Summer's hosting connection and verify HTTPS. Returns pending until each check succeeds.
Inputs: company (required), expected_version (required), idempotency_key.
Read the exact current draft, article revisions and authenticated preview URL before publishing. No public access token is issued.
Inputs: company (required).
Publish a complete release of the company's customer help center. The release replaces every published article: list each article that should stay public (guides.preview publication.articles) and name any published article you mean to remove in unpublish. Requires explicit publication authority; does not approve customer business actions.
Inputs: reason (required), company (required), articles (required), expected_version (required), +2 more.
Create or edit guidebook details at the expected version. Saves a private draft; does not publish.
Inputs: reason (required), company (required), settings (required), expected_version (required), +1 more.
Remove the company's guide and release media from Summer's public serving path at the expected version. Downloaded copies cannot be recalled.
Inputs: reason (required), company (required), expected_version (required), idempotency_key.
Read 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.
Inputs: company (required), environment (required), case, mine, +2 more.
Complete, dismiss, reopen or assign a human task with its expected version. Records the person and outcome. Does not approve a plan or change customer records.
Inputs: taskId (required), company (required), version (required), operation (required), +4 more.
Start, pause, resume or rescan an Intercom migration with its current version. Optional incremental sync reconciles the same original IDs; no replies, notifications or agent runs. Names/email never verify an account.
Inputs: action (required), import (required), company (required), environment (required), +3 more.
Read Intercom migration previews, saved progress, counts, errors and Summer inbox destinations. Does not start an import.
Inputs: company (required), environment (required).
Check the saved Intercom key against a workspace and preview contact/conversation counts. Save the selected Summer inbox and explicit account-matching choice. Import nothing; send nothing.
Inputs: company (required), workspace (required), environment (required), installation (required), +3 more.
Search imported Summer profiles and their original conversation references. Contact details do not establish account ownership.
Inputs: company (required), workspace (required), environment (required), q, +1 more.
List provider integrations, their categories, required fields, alternative credential sets and saved metadata. Filter by search, category or connection. Connected means all required credentials and one complete alternative set are available, not a live provider check. read_only integrations are read with the company's own key and never written through. Never returns values.
Inputs: company (required), environment (required), search, category, +1 more.
Save a custom integration's description, setup instructions and credential field names. This saves metadata only, without credential values or a live connection check.
Inputs: name (required), fields (required), company (required), environment (required), +5 more.
Prepare an integration-specific MCP setup prompt and Codex or Claude Code app links. Includes the selected company, environment and setup brief, never credential values. Does not launch an app or change configuration.
Inputs: name (required), company (required), environment (required), id, +3 more.
Read shared investigation runs, saved plans, approval state and execution receipts across the verified customer’s cases, including historical issues. Each run retains its original support_case_id; use that ID for write operations and original run evidence.
Inputs: case (required), company (required), environment (required).
Edit wording or skip steps in the current saved plan at its expected revision, including proposed company knowledge text. Step IDs are native for delegated work and effect:0, effect:1 and so on in the selected option's original order. Skipped steps stay in the plan, never run and are named to the executor. Returns every step and whether it is skipped. Preserves targets, amounts, feedback sources and selected option. Invalidates prepared approval; does not apply knowledge or customer changes.
Inputs: case (required), reason (required), company (required), request (required), +5 more.
Ask Summer to investigate the case, or revise a saved plan with feedback. The new plan follows the company's auto-run rules; to make every plan wait for a person, turn auto-run off in the execution policy. Guidance and feedback apply to this request only; later plans read them as past context. Set guidance_scope to standing for an instruction that applies to every later plan for this customer.
Inputs: case (required), company (required), request (required), environment (required), +1 more.
Stop an exact investigation owned by this case, preserving its evidence and history. Cannot stop execution runs. A stop request is not a finished cancellation: read investigations.list until the run is cancelled or completed, then use investigations.request with current guidance to rerun.
Inputs: run (required), case (required), company (required), environment (required), +1 more.
Adopt an exact published shared version with company-admin authority, expected adoption revision and reason. Preserves local company policies and prior agent snapshots.
Inputs: reason (required), company (required), profile (required), version (required), +2 more.
Read current and latest shared publication versions, adoption history and the company's business profile.
Inputs: company (required).
Read company knowledge changes from people, delegated API/MCP connections and Summer agent plans, with before/after revisions, GPT change summaries, summary processing state and original provenance. Set actor=summer for Summer plans and Teach Summer edits.
Inputs: company (required), actor, offset.
Upload a new company knowledge document with original revision history. The shared library is used by all roles and environments. Existing document IDs are refused. API reference: https://api.gosummer.ai/v1/openapi.json
Inputs: id (required), path (required), reason (required), company (required), +3 more.
Edit an existing company knowledge document with the expected revision and a reason. Affects every environment and later runs.
Inputs: reason (required), status (required), company (required), content (required), +3 more.
Read the effective knowledge manifest and exact shared/company document revisions used by agents, including provenance and published customer guide links.
Inputs: company (required).
Read one company knowledge document and its current revision.
Inputs: company (required), document (required).
Read the edit history of a company knowledge document with GPT change summaries and processing state. Set actor=summer for Summer plans and Teach Summer edits.
Inputs: company (required), document (required), actor, offset.
List current company knowledge documents. Knowledge is company-wide, not per environment. Pass tag to list documents with that tag, such as an integration name (slack, beluga, mdi), which is how Summer shows knowledge related to an integration.
Inputs: company (required), tag, query, offset.
Read all waiting and sending Summer messages across email, Slack, texts and website chat for a company/environment. Includes paced replies, office-hour queues and company-wide Slack setup messages, original recipients, saved text, next eligible send times and case links. Filter by channel and page with offset/limit. Counts cover the whole queue. Changes nothing and never sends or retries a message.
Inputs: company (required), environment (required), limit, offset, +1 more.
Open the Summer workspace for a human to choose a queued message and click Send now outside sending hours. Returns a UI handoff only; API, CLI and MCP callers cannot override hours or send a message. The signed-in person must have current sending access. Consent, ordering, exact approvals and original receipt checks remain enforced.
Inputs: company (required), environment (required).
Read assistant settings per installation and whether the managed runtime is enabled.
Inputs: company (required), environment (required).
Update assistant instructions and escalation permission with the expected revision. Company facts live in shared knowledge. Cannot raise the spending limit.
Inputs: company (required), revision (required), settings (required), environment (required), +2 more.
Apply an exact backfill preview using saved settings. Queue unanswered conversations and fresh investigations of qualifying pending plans, up to 100 items. Enabled assistants may reply; new plans follow saved auto-run settings. Skips paused, active, failed or uncertain work. Does not replay old executions. Requires the exact preview_hash; changed settings or work require a new preview. Repeating a successful hash returns its saved receipt.
Inputs: company (required), environment (required), preview_hash (required), idempotency_key.
Legacy channel policy only; unavailable after an explicit company-policy replacement. Preview existing Messenger work under saved autonomy settings: counts, a plan confidence histogram and a preview_hash. Returns no messages or customer records. Starts nothing. Up to 100 items per apply batch; totals cover all matching work.
Inputs: company (required), environment (required).
Read the company execution policy and its publishing history, plus autonomy for website chat, texting and email: whether the assistant gives fast replies and how sure it must be to answer alone, and the auto-run plan settings, including who turned auto-run on and website chat installation readiness (chat_assistant).
Inputs: company (required), environment (required).
Change one channel's autonomy with the expected version. With fast reply on, the assistant handles that channel's messages and starts a plan only when it escalates. A lower threshold gives it more autonomy.
Inputs: channel (required), company (required), version (required), environment (required), +5 more.
Pause the assistant in one conversation so a person can take over, or ask it to resume. Pausing stops automatic replies immediately.
Inputs: paused (required), company (required), environment (required), conversation (required), +1 more.
Read original Messenger messages with saved human sender_display_name, contact form details, read receipts, attachments and timestamped page_context (current page and UI controls) without marking the chat read.
Inputs: company (required), environment (required), conversation (required), view, +3 more.
Search and filter the complete Messenger inbox, including visitor conversations without Ops cases.
Inputs: company (required), environment (required), q, sort, +4 more.
Check forwarding, the DNS record and sending status for one support email address now. Records the latest sending status; sends nothing.
Inputs: channel (required), company (required), environment (required).
Add a support email address. Summer creates its private forwarding address and signing key and returns the DNS record to add. The address starts off; nothing is sent.
Inputs: company (required), environment (required), display_name (required), support_address (required), +2 more.
Read support email addresses: the private forwarding address, the one DNS record to add, whether mail has arrived, sending status, Gmail forwarding codes and emails that need a look.
Inputs: company (required), environment (required).
Change the sender name or turn a support email address on or off, with the expected version. Turning on needs one received email. Turning off keeps every email but stops new conversations and replies.
Inputs: channel (required), company (required), version (required), environment (required), +3 more.
Create an installation with a client-chosen ID. The one-time signing key goes to the trusted local helper, never to model-visible output. Returns a local CLI command when a secret is involved.
Inputs: id (required), company (required), settings (required), environment (required), +1 more.
List Messenger installations in this environment. Signing keys are never returned.
Inputs: company (required), environment (required).
Issue a new signing key. Existing signed sessions end. The key goes to the trusted local helper only. Returns a local CLI command when a secret is involved.
Inputs: company (required), environment (required), installation (required), expected_version (required), +1 more.
Update installation settings with the expected version. Keeps the signing key.
Inputs: company (required), settings (required), environment (required), installation (required), +2 more.
Read consented website leads for this company and environment. Includes volunteered contact details and original submission references.
Inputs: company (required), environment (required), before.
Add a texting line. Received texts on it can join Summer conversations. The line starts off; nothing is sent. Fast replies follow the texting channel's autonomy setting.
Inputs: company (required), environment (required), persona_name (required), quo_phone_number_id (required), +7 more.
Read texting lines: each line's persona name, how it hands work to the team, reply hours and whether texts join conversations, plus recent send problems and the lines this deployment can text from. Whether the assistant replies is a channel autonomy setting.
Inputs: company (required), environment (required).
Change a texting line with the expected version: persona name, handoff wording, reply hours, other Quo lines it takes texts in from and whether texts join conversations. Turn fast replies on or off in messenger.autonomy.update.
Inputs: line (required), company (required), version (required), environment (required), +8 more.
Read voice chat settings per installation, the voice services and their voices, published help article count and the voice assistant's update status.
Inputs: company (required), environment (required).
Update voice chat settings with the expected revision. Summer updates the voice assistant from these settings and the company's published help articles.
Inputs: company (required), revision (required), settings (required), environment (required), +2 more.
Apply a reviewed saved policy draft to exact company knowledge revisions with company-admin authority and audit history. forLaunch checks the selected company AI employee and four company facts; other policies are optional. Shared clinical/identity/approval boundaries remain. Does not publish public articles, activate integrations, change hours/billing or approve customer effects. Existing operations libraries use their normal knowledge editor.
Inputs: reason (required), company (required), expectedRevision (required), documentRevisions (required), +2 more.
Read the existing AI employee choices and four explained company questions, five optional policy preferences, current answers, connected channel/teammate/patient-portal choices, exact preview and agent setup instructions. Company branding is already known. No long questionnaire is returned.
Inputs: company (required).
Save any partial policy answer patch, including answers researched by an authorized agent with website/code/knowledge sources and notes. useStarterDefaults with the current catalogVersion selects starter policies and fills the five optional preferences, preserving existing tailored policies. Choose the company AI employee by employeeId; known destinations can use an owned selection reference; missing facts have no invented default. Empty answers are allowed. Draft only, no runtime activation; skip any or all questions.
Inputs: answers (required), company (required), catalogVersion (required), expectedRevision (required), +2 more.
Read readiness separately for public support and account/order support, actual activation, relevant check freshness, provider account state and adopted shared guidance. Optional unfinished providers do not block unrelated working capabilities. Saved keys and templates do not establish readiness.
Inputs: company (required), environment (required).
Remove a partner contact. Mail or Slack posts to it go back to an unknown audience. The entry and the reason stay in the history.
Inputs: id (required), reason (required), company (required), environment (required), +1 more.
Name an email address, an email domain or a Slack channel as a partner or as your own team. Summer then knows who vendor mail and Slack replies reach, so they can run on their own under the company policy instead of waiting as an unknown audience. Saving an existing entry changes its audience or label.
Inputs: kind (required), value (required), company (required), audience (required), +3 more.
Save a confirmed administrative shipping-address correction for the selected order on a live outbound pharmacy call. Requires an Ops admin and customer-effect access. Does not update carriers or clinical fields; cross-state requests go to clinical coverage review.
Inputs: caseId (required), address (required), call_id (required), company (required), +2 more.
Read the pharmacy directory: each pharmacy's phone number and where it was checked, time zone, hours, phone menu keys, what it asks for, preferred channel, whether calls are on, notes, whether Summer may call it now and why not, removed pharmacies and change history. Starts no call.
Inputs: company (required), environment (required).
Add, change, remove (retire) or restore one pharmacy in the directory with the expected version. Save sends every field; empty fields are cleared. Calls stay off until call_allowed is true, and need a phone number. Retire turns calls off and keeps the record and its history. Starts no call.
Inputs: company (required), version (required), operation (required), environment (required), +3 more.
Read demo pharmacy-call voice service, voices, vocabulary and change history. Starts no call.
Inputs: company (required), environment (required).
Save the demo pharmacy-call voice service, voice and vocabulary with the expected revision. provider is openai_live (OpenAI GPT-Live, default) or elevenlabs; omitted provider or openai_voice keeps the saved value. Starts no call.
Inputs: company (required), revision (required), voice_id (required), vocabulary (required), +4 more.
Read Summer answering lines, Quo number and keypad mappings, recent calls, source digits, case links, received-event times and settings history. Does not mark calls read or change Quo routing.
Inputs: company (required), environment (required).
Save Summer answering and call-type mappings for an existing line with its expected version. Requires current company and Ops admin access. Does not publish a Quo menu, change ringing users or forward a number. New Quo numbers also need webhook subscription in Quo.
Inputs: menu (required), company (required), enabled (required), line_id (required), +5 more.
List published plans, newest first: who approved each (a person or an agent), whether it ran and was checked, the agent's self-review, its own call on running the plan without approval, and auto_run: what the channel's auto-run setting did or would do with it (outcome ran/would_run/would_wait, the deciding reason, channel, on/off, confidence bar and any saved auto-run decision), and runs_as: code when approved work runs, or ran, without an agent (a plan that only resolves the case, or sends one reply and then resolves it), otherwise agent. Includes totals comparing the agent's calls with people's decisions. Read-only.
Inputs: company (required), environment (required), call, show, +2 more.
File an export or deletion request for human review. Cannot approve, perform or attest completion of the work.
Inputs: id (required), kind (required), scope (required), reason (required), +5 more.
Read privacy export/deletion requests, status and original event history. Does not export or delete data.
Inputs: company (required).
Read company-owned clinician/provider account configuration and actual verified capabilities. Credential names only; no values.
Inputs: company (required), environment (required).
Save provider account metadata at an expected revision or disconnect it. Changes invalidate previous checks and disable its capabilities. This does not assert a working Bask API or verify credentials.
Inputs: id (required), region (required), company (required), provider (required), +7 more.
Record an evidence-backed assessment or correction. Does not approve a plan or customer action.
Inputs: id (required), kind (required), notes (required), checks (required), +7 more.
Read evidence-backed corrections to previous quality assessments.
Inputs: company (required).
Read one scenario and its saved assessments.
Inputs: company (required), scenario (required).
Read quality scenarios, assessments and current outcomes.
Inputs: company (required).
Create, revise or retire a quality scenario, with expected revision and reason.
Inputs: id (required), kind (required), fields (required), reason (required), +4 more.
Read 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.
Inputs: company (required), environment (required), days.
Read 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.
Inputs: company (required), environment (required).
Read 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.
Inputs: company (required), environment (required), days.
Read 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.
Inputs: company (required), environment (required), days, revenue.
Read outstanding customer promises and unfinished work.
Inputs: company (required), environment (required).
Read 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.
Inputs: company (required), environment (required).
Read delivery attempts, failures and recorded results. Does not retry a delivery.
Inputs: company (required), environment (required).
Read 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.
Inputs: company (required), measure (required), environment (required), from, +7 more.
Read 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.
Inputs: company (required), environment (required).
Generate a private recurring-issue report from the admitted case-summary cohort. One immutable request ID prevents duplicate inference. No customer, knowledge or publication effect.
Inputs: to (required), from (required), company (required), request_id (required), +2 more.
Read one saved recurring-issue report and its source snapshot, including reports older than the latest list. Requires current operational company access.
Inputs: report (required), company (required), environment (required).
Read the latest private recurring-issue reports, original case references, source coverage, generation status and human review. Generated themes are suggestions, not verified causes.
Inputs: company (required), environment (required).
Record 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.
Inputs: theme (required), reason (required), report (required), company (required), +4 more.
Read 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.
Inputs: company (required), environment (required), period.
Read 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.
Inputs: company (required), days, rule, route, +2 more.
Read every saved revision of the router rules, with who changed them and why.
Inputs: company (required).
Read 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.
Inputs: company (required).
Check 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.
Inputs: company (required), days, rules, intake, +1 more.
Save 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.
Inputs: rules (required), reason (required), company (required), version (required), +1 more.
List investigation and execution runs across cases, newest first, with status, plan approval and date filters.
Inputs: company (required), environment (required), kind, sort, +5 more.
Configure this company's runtime and pilot at the current revision. Production activation requires current readiness evidence. Preserves budgets and exact effect approval; automatic investigations prepare plans and do not enable automatic actions.
Inputs: company (required), effects (required), enabled (required), version (required), +8 more.
Read the company runtime connection, capability switches, pilot cases, automatic investigation setting and original configuration history.
Inputs: company (required), environment (required).
Read original revisions of a saved reply.
Inputs: reply (required), company (required).
Read company saved replies, optionally including retired replies.
Inputs: company (required), retired.
Create, edit, retire or restore a saved reply with its expected revision and reason. Sends nothing. API reference: https://api.gosummer.ai/v1/openapi.json
Inputs: id (required), body (required), name (required), reason (required), +4 more.
Remove an owned inbox view, retaining the database's ownership checks.
Inputs: id (required), kind (required), company (required), idempotency_key.
Read this person's saved inbox views and shared company views.
Inputs: company (required).
Save a personal or shared inbox view. Known case filters are normalized by the same service as the UI.
Inputs: id (required), kind (required), name (required), query (required), +3 more.
Read saved scheduled-job definition revisions and authenticated edit reasons.
Inputs: job (required), company (required), environment (required).
Read company scheduled agent jobs, names, instructions, schedules, next runs and latest results. These independent jobs use company knowledge and connected tools; source collection precedes ordinary case routing.
Inputs: company (required), environment (required).
Request one run of an enabled scheduled job. Concurrent and repeated requests coalesce; reuse request_id on retry. The job's normal schedule remains in place.
Inputs: job (required), company (required), request_id (required), environment (required), +2 more.
Read recent scheduled runs with original definition revisions, outcomes, coverage, saved source counts and failures.
Inputs: job (required), company (required), environment (required).
Create or update a scheduled native agent job at its expected revision. Configure its name, instructions, interval or five-field cron, IANA timezone and enabled state. Pausing stops an active run. Requires company admin and automation.manage; grants source reads and evidence capture, never customer effects.
Inputs: id (required), name (required), reason (required), company (required), +7 more.
List the company's service accounts.
Inputs: company (required).
Create, update, rotate or disable a service account. A new secret goes to the trusted local helper only. Returns a local CLI command when a secret is involved.
Inputs: name (required), scopes (required), account (required), company (required), +5 more.
Disconnect the caller's own Slack account from Summer in this company and delete its saved token. Replies set to post as the approver are then blocked for the caller, and Summer stops reading as the caller.
Inputs: company (required), idempotency_key.
Read whether the caller's own Slack account is connected to Summer in this company, and the settings link to connect it. Connecting uses Slack sign-in in a browser.
Inputs: company (required).
Set which vendor a selected Slack channel is for and what it is used for, with a reason. Null clears a field. Changes guidance for agents and people; sends no message and changes no channel access.
Inputs: reason (required), vendor (required), channel (required), company (required), +3 more.
List the Slack channels the company selected for Summer, with read and post access and each channel's vendor and purpose. Agents see the vendor and purpose with every vendor Slack read.
Inputs: company (required).
Allow or stop approved agent replies in one vendor Slack channel, with the expected version from teammates.setup.status and a reason. Each reply still needs a person to approve its exact text. Sends no message.
Inputs: reason (required), allowed (required), channel (required), company (required), +2 more.
Read connected Slack posting channels, or inspect current channel name/privacy, posting revision and authenticated sender. Use audience vendor for a company-labelled vendor channel, including shared channels; internal is the default. Enables no grant and posts nothing.
Inputs: company (required), environment (required), channel, audience.
Read the support name and avatar shown on Summer's approved Slack replies, whether the Slack install allows them, and the change history.
Inputs: company (required).
Set the support name and avatar on Summer's approved Slack replies, with the expected revision and a reason. Null values use the plain Summer Ellis identity. Sends no message.
Inputs: reason (required), company (required), revision (required), avatar_url (required), +2 more.
Read which Slack account Summer links to the caller in this company, how it was linked, the Slack people the caller can choose from, and whether Summer sends the caller Slack messages about assigned human tasks.
Inputs: company (required).
Admin: match every company member to their Slack account again, by email and name. Accounts people signed in with or chose stay as they are. Runs within a few minutes; sends no message.
Inputs: company (required), idempotency_key.
Choose the caller's own Slack account in this company, say they have none, or turn Slack messages about their human tasks on or off. Changes only the caller's settings.
Inputs: company (required), none, notices, slack_user_id, +1 more.
Read who Summer reads Slack as: the connection itself (the Summer app or the installer's personal read access), an AI employee, or an admin's own Slack account, whether that account is connected, the revision and the change history.
Inputs: company (required).
Choose who Summer reads Slack as, with the revision from slack.reader.read and a reason. 'me' uses the caller's own connected Slack account; nobody can choose another person's account. Summer reads only the selected channels that account can see. Sends no message.
Inputs: reader (required), reason (required), company (required), revision (required), +2 more.
Choose who posts approved vendor Slack replies: the Summer Ellis app, a Summer Teammate (AI employee) from its own Slack account, or the person who approves each reply, from their own connected Slack account. Uses the revision from slack.identity.read and a reason. Sends no message.
Inputs: reason (required), company (required), revision (required), teammate_id (required), +2 more.
Read business hours, holidays, response commitments and scheduled policy revisions. These business hours also govern queued Summer Slack posts; without an effective revision Slack defaults to Monday–Friday, 9am–5pm America/Los_Angeles.
Inputs: company (required).
Save business hours and response commitments with the expected revision and an effective date. The effective calendar also sets Summer Slack sending hours, including timezone and holidays; queued posts recheck it before delivery.
Inputs: reason (required), company (required), calendar (required), commitments (required), +4 more.
Add a teammate. A managed teammate gets first.last@gosummer.ai, unique across Summer. A company-managed teammate uses the company's own address. Invites no one, joins no Slack workspace and sends nothing.
Inputs: company (required), request (required), idempotency_key.
List the company's teammates with their address, photo, status, unread mail count and Slack connection.
Inputs: company (required).
Read one message in a Summer-managed teammate's mailbox, including its text. Marks it read for the team.
Inputs: company (required), message (required), teammate (required).
List mail received by a Summer-managed teammate, newest first, with sender, subject and a short preview. Company-managed teammates have no mailbox in Summer.
Inputs: company (required), teammate (required), limit, before.
List suggested female and gender-neutral teammate names whose gosummer.ai address is still free. Each has a suggested photo_url to show; create with use_suggested_photo: true to add that name, address and photo together. Any typed first and last name also works.
Inputs: company (required).
Live status of each step to get a teammate posting approved replies in vendor Slack channels: Slack connected, teammate added, Slack invitation received, teammate connected, chosen as sender, in each vendor channel, and agent replies allowed there. Unreadable sources are reported as unknown.
Inputs: company (required).
Join a public Slack channel as the connected teammate. Sends no message. A private or shared channel needs someone in it to /invite the teammate in Slack.
Inputs: channel (required), company (required), teammate (required), idempotency_key.
Disconnect a teammate's Slack account from Summer and delete its saved token. The Slack account itself stays in the workspace. Connecting needs the Slack sign-in in Summer settings.
Inputs: reason (required), company (required), teammate (required), idempotency_key.
List the people who can DM this AI employee in Slack, with the list revision, plus people: names and member IDs Summer has seen in the selected channels, to choose from. Each DM from one of them opens an Ops case; a person approves the exact reply before the AI employee posts it. Needs a company owner or administrator.
Inputs: company (required), teammate (required).
Add or remove one person who can DM this AI employee, with the expected list revision and a reason. Summer reads only DMs from people on the list. Removing someone stops Summer reading and posting in that DM. Sends nothing.
Inputs: reason (required), allowed (required), company (required), revision (required), +3 more.
Make a one-time link that connects the teammate's Slack account. Open it in the browser signed in to Slack as the teammate and select Allow; no Summer sign-in is needed there. It works once, for 15 minutes, and the connection is recorded as yours. Treat the link like a password. Needs a company owner or administrator.
Inputs: company (required), teammate (required), idempotency_key.
Change a teammate's shown name, photo or status, with the expected revision and a reason. Retiring disconnects Slack and keeps the address reserved.
Inputs: reason (required), status (required), company (required), revision (required), +4 more.
Run supported harmless checks. Unsupported checks are reported as unsupported, never as passed.
Inputs: company (required), targets (required), environment (required), idempotency_key.
List webhook endpoints and delivery state.
Inputs: company (required), environment (required).
Queue past events after a cursor for delivery again to one endpoint. Receivers deduplicate by event ID.
Inputs: after (required), company (required), webhook (required), environment (required), +2 more.
Create, update, rotate or disable a signed webhook endpoint. A new signing secret goes to the trusted local helper only. Returns a local CLI command when a secret is involved.
Inputs: url (required), company (required), webhook (required), environment (required), +5 more.
Read the original revisions and authenticated edits for a saved workflow.
Inputs: company (required), workflow (required), environment (required).
Read built-in tasks and company/environment-owned workflow templates. Selecting one never runs work.
Inputs: company (required), environment (required), retired.
Prepare editable operator guidance from an exact active workflow revision and feedback. Starts no investigation and executes no action.
Inputs: id (required), company (required), environment (required), expected_revision (required), +1 more.
Save, retire or restore a task template with its expected revision. Changes no case or effect authority.
Inputs: id (required), name (required), reason (required), company (required), +6 more.
Read eligible teammates and automatic routing for new issues, plan reviews and human tasks.
Inputs: company (required).
Save automatic routing for new issues, plan reviews and human tasks with the expected version. Does not grant roles or approval authority.
Inputs: company (required), version (required), issue_mode (required), review_mode (required), +5 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.