Keiki MCP
Build and manage Keiki agents, conversations, evaluations, channels, billing, integrations, and organization settings through the official hosted MCP server.
336 actionsAPI key
What your bot can do in Keiki MCP
Looks up
- Check jobRead a job that a long call handed back instead of a result.
- Current contextWho this token acts as, which organization it is bound to, and the current time.
- Get agent goalsThe outcome kinds each agent has produced and whether any carry money — what an agent’s CRM columns stand for.
- Get agent groupsList the organization’s agent groups — which agents may ask each other with ask_agent — with each group’s name, description and members…
- Get agent groups activityEvery agent group’s running peer threads and live roster in one read — the way to answer how all the groups (swarms) are doing at once.
- Get agent groups noteThe group’s shared note — what its agents have settled among themselves (decisions, who does what, findings) — with its revision, last…
- Get agent groups note versionsHistory of the group note, newest first.
- Get agent groups note versions by shaThe group note body as it was at one historical version (a sha from the versions list).
- Get agent groups rosterLive roster of one group.
- Get agent groups threadsThe asker→peer threads currently live among one group’s members (who is asking whom right now).
Show 145 more
- Get agent templatesComplete agent templates the platform can provision in one call (e.g.
- Get agentmail domainsCustom email domains the organization added for agent inboxes, each with its region and live DNS verification state from AgentMail.
- Get agentsList every agent in the organization with its status, model and channels.
- Get agents a2aWhether other vendors’ agents can call the agent over A2A, with its Agent Card URL and JSON-RPC endpoint.
- Get agents actionsList the agent’s persisted approval actions (tool calls waiting on, or past, a human decision), newest first, with their status, arguments…
- Get agents analyticsEngagement for one agent over a date range.
- Get agents api gatewayWhether the agent answers on the OpenAI/Anthropic-compatible API and in passthrough mode, with the base URLs and the model name a client…
- Get agents by idAgent detail.
- Get agents capabilitiesList the marketplace capabilities installed on an agent, including disabled ones, with each pinned version, how it was installed, any…
- Get agents conversationsEvery conversation one agent is having, newest first — who it is talking to, the last message, message count, whether the thread is active…
- Get agents conversations by phoneOne conversation thread between the agent and a contact (phone is their phone number, email or tg.
- Get agents conversations sentimentOne conversation’s mood per user turn, oldest first (0 angry to 4 delighted.
- Get agents editThe agent form payload.
- Get agents evals channel previewPreview a real-channel eval run per hosted driver (imessage, email, x).
- Get agents fine tuneRead fine-tune readiness for the agent’s current version.
- Get agents harness statusReport what runs the agent and whether it is connected.
- Get agents loopsList the scheduled loops attached to an agent with their schedule and state.
- Get agents loops runsRead a loop’s recent runs, newest first, from a bounded retention window.
- Get agents mcp presets toolsThe tools a connected MCP exposes, read live from the daemon, each with the permission (allow/ask/deny) in force, plus the default…
- Get agents noteRead the agent’s working note — the durable scratchpad it rewrites while it works — with its revision.
- Get agents note versionsList the working note’s version history, newest first, with the sha of each version.
- Get agents note versions by shaRead the working note body as it was at one version sha from the history.
- Get agents public profileWhether the agent’s public profile page is published, its URL slug and tagline, and whether the caller may change it.
- Get agents qualityTurn-quality review for one agent.
- Get agents rolloutsRead the agent’s open staged rollout (mode, percent of conversations on the staged config, the staged config itself) and its recent ended…
- Get agents sandbox script runsThe latest 50 runs of the agent’s sandbox scripts, newest first — status, exit code and output tails.
- Get agents shared lineThe shared iMessage number and join code contacts text to reach this agent.
- Get agents signalsBuilt-in quality signals for one agent over a date range.
- Get agents signals eventsThe turns one signal (key, as returned by the signals summary) fired on, newest first.
- Get agents user connectionsList the personal provider definitions declared on the agent — services each conversation user authorizes with their own account.
- Get agents versionsList the agent configuration’s version history, with the sha of each version.
- Get agents versions by shaRead the agent configuration snapshot saved at one version sha.
- Get agents walletThe agent’s wallet.
- Get agents wallet payment methodsLabelled payment methods on the wallet’s connected account (never card numbers), for choosing paymentMethodId.
- Get auditList audit events as { events, nextCursor }.
- Get audit verifyVerify the organization audit hash chain and return its verification result.
- Get autoRead whether the organization’s plan allows Auto mode and which front and worker models it uses.
- Get axiom tracesSpans read from the OTLP collector — kept past the 14-day window of /traces, and alongside spans other services exported under the same…
- Get billingRead the organization’s billing overview.
- Get billing activityList the organization’s invoice and platform credit grant activity, newest first.
- Get billing auto top upRead the organization’s auto top-up settings.
- Get billing capability pricingRead the default plan’s per-capability billing metadata, included amounts, units and price labels.
- Get billing capability usage by agentRead local capability usage grouped by feature and agent for each feature’s latest recorded billing period, including unattributed and…
- Get billing consumer pricingRead public consumer plans, add-ons and feature pricing metadata from the billing catalog.
- Get billing included allowanceRead public default-plan included token-credit allowances without customer data.
- Get billing plansList the organization’s available non-add-on, non-archived plans with display prices, features, trial information and current/scheduled…
- Get billing pricing accountRead the connected organization’s current plan and status, usage and credit access checks.
- Get billing public plansRead public recurring plans with included limits and platform credit conversion rates for comparing options.
- Get billing service spendRead the organization’s recorded customer service charges for the billing period.
- Get billing statusCheck the organization’s lightweight plan gate rather than loading its billing overview.
- Get billing usage by conversationList up to 100 conversations with the most recorded token usage across the organization’s active developer configurations, excluding…
- Get blogKeiki's own blog, newest first.
- Get blog by slugOne Keiki blog post in full.
- Get capability toolsEvery platform capability offered on this deployment and the tools each adds to an agent that enables it, as feature, tool name and tool…
- Get channel access requestsList organization early-access requests as { requests }.
- Get conversationsOne page of the organization’s conversations, most recent first, each with its agent, identity and latest state.
- Get conversations by phoneOne conversation thread by identity (phone number, email, or prefixed id like tg.
- Get conversations contact cardRead the contact card set specifically for this conversation, and whether dynamic contact cards are available.
- Get conversations countHow many conversations match the same filters as the conversation list, and how many of those need a person.
- Get dashboardHome-page summary for the signed-in user.
- Get deploymentRead one deployment in the current organization.
- Get evals casesList the organization agent’s persisted eval cases, including generated, user-authored and regression cases.
- Get evals cases versionsRead the generated eval suite’s version history for an agent in the organization.
- Get evals diffsCompare two organization eval runs as their results arrive.
- Get evals runs by idRead one organization eval run’s status, candidates, rankings and per-case results with trace ids.
- Get evals runs casesRead the full persisted case records referenced by an organization eval run, including archived cases.
- Get evals runs latestRead the agent’s latest eval run, optionally limited to single-model, sweep or real-channel runs.
- Get evals runs transcriptRead an organization real-channel eval run’s recorded message transcript.
- Get evals suggestionsFind behaviors worth testing from the agent’s recorded production traffic in the chosen window, with trace counts, error rates, models and…
- Get identitiesList the org’s active messaging identities — SMS lines, Telegram, WhatsApp, Slack, Teams, X and AgentMail — with the agent each is…
- Get identities phone calls forwardable linesList the agent's iMessage lines and whether each can forward its calls.
- Get identities phone calls numbersSearch Telnyx for available US local voice numbers in an area code or state, or anywhere in the US when neither is given.
- Get identities phone calls voicesList the ElevenLabs voices a phone line can use.
- Get identities slack channelsPer workspace that installed this Slack identity, the channels its bot is already in — the channel ids an escalation route may name — plus…
- Get identities slack manifestBuild the Slack app manifest for a new identity and a prefilled api.slack.com app-creation URL, plus the events, interactivity and OAuth…
- Get identities slack operatorsList the Slack users allowed to press this identity’s consequential buttons — taking a conversation over, replying to a customer, running…
- Get identities slack signing probe by probe idCheck a Slack signing-secret probe.
- Get identities slack teamsFor a Slack app that routes customer workspaces to different agents, list each workspace.
- Get identities teams manifestThe Teams app manifest for a connected Teams identity — it names that identity’s Microsoft App ID.
- Get identities teams setupReturn the messaging endpoint an Azure Bot registration must point at before a Teams identity can be connected.
- Get identities whatsapp kapso availableRead platform Kapso configuration as { available }.
- Get identities x oauth availableWhether “Log in with X” can be offered — an X OAuth client is configured — plus which app-level credentials the platform already has, the…
- Get identities x oauth statusPoll a started X login.
- Get insightsOrg analytics over a date range.
- Get invitationsList the organization’s invitations, newest first, with email, role, status (pending, accepted or revoked) and expiry.
- Get keysList the organization’s API keys.
- Get keys usageDaily usage of one API key, aggregated by day, by route and method, and by agent, with accepted vs rejected (revoked/expired) counts and…
- Get linesList the organization’s phone lines with channel, line type, routing status and message, activation time, and the agent each is assigned to.
- Get lines contact cardRead the contact card iMessage shows for a line — first and last name, photo URL, and whether the provider has applied it — straight from…
- Get lines priceThe display price of a new iMessage line (price, e.g.
- Get lines providersStatus of each iMessage line provider (Photon, Linq, Blooio) as shown on the status page.
- Get lines provisioning by idProgress of one of the organization’s line purchases.
- Get live snapshotWhat the org’s agents are doing right now.
- Get loopsList the organization’s scheduled loops, newest first.
- Get marketplace capabilitiesBrowse published (reviewed) marketplace capabilities, one listing per capability with its newest version and the other versions available…
- Get marketplace mineList the capabilities this organization has published itself, in every review state (draft, pending review, published, rejected).
- Get marketplace reviewsList the capabilities awaiting publication review.
- Get mcp brand lookupResolve the brand behind an MCP server endpoint URL — its name, domain, description and logo.
- Get mcp catalogSearch the approved integrations.sh catalog of connectable services (name, domain, description, kind, icon, categories).
- Get mcp catalog by domainResolve one catalogued domain into its connectable surfaces — MCP endpoints, OpenAPI/GraphQL specs and CLIs — with each surface’s URL,…
- Get mcp clientsList this user’s organization OAuth connections as { connections }.
- Get membersList the members of the connected organization with their role and last sign-in, plus the caller’s own user id and role and whether the…
- Get modelsSearch the models an agent can run on — ids, context window, price per million tokens, and tool, reasoning and vision support.
- Get notificationsThe signed-in user’s daily digest preference (digestOptOut) and the timezone the digest is sent in (null when none was reported).
- Get org mcp integrationsList the organization-owned MCP integrations.
- Get orgsList every organization the signed-in user belongs to, with their role and logo in each, plus the id of the currently active organization.
- Get orgs brand logoLook up the brand logo URL for a domain.
- Get orgs currentRead the active organization’s id, name, logo domain and logo URL, and whether the caller may edit it (canManage).
- Get orgs current build recommendationsRead the agent ideas Home shows for the active organization.
- Get outcomesRecorded business outcomes — sales, bookings, qualified leads — newest first, with totals per kind for the same agent, person and time…
- Get paymentsRead the organization’s Grosso payments account.
- Get payments payeesRead the organization’s newest 100 Grosso payees (businesses it collects payments for).
- Get peopleDirectory of the people behind the organization’s conversations, most recently seen first, with the total matching count.
- Get people by person idOne person.
- Get provider accountsList the organization’s own Photon accounts connected to Keiki.
- Get sandbox providersRead sandbox provider availability as { providers }.
- Get sandbox scriptsList the org’s sandbox scripts with the agents running each and its newest run — where a script that fails every boot shows up.
- Get sandbox scripts by idRead one sandbox script, including its body, targets, timeout and env secret names.
- Get sandbox scripts runsEvery sandbox run of one script across its agents, newest first — status, exit code and output tails.
- Get sandbox scripts versionsVersion history of a sandbox script, newest first — each entry carries the commit sha to read it at.
- Get sandbox scripts versions by shaRead a sandbox script’s body as of one version, by the sha from its version history.
- Get secretsList the organization’s developer secret names with created/updated times and any host binding.
- Get signalsBuilt-in quality signals across every agent in the org, or one agent.
- Get skillsList the org’s skills and knowledge documents (metadata, no body) with the agents each is attached to.
- Get skills by idRead one skill or document, including its full body.
- Get skills presetsList the built-in preset skills (id, capability, name, description, kind) and whether the org already added each.
- Get skills versionsVersion history of a skill, newest first — each entry carries the commit sha to read it at.
- Get skills versions by shaRead a skill’s body and metadata as of one version, by the sha from its version history.
- Get ssoRead SSO connection, domains, eligibility and platform configuration.
- Get trace exportersList the destinations the org ships finished turns to — format, endpoint, header names (never values), enabled, attached agent ids, last…
- Get tracesList one page of the org’s agent turns (traces), newest first, with status, model, tokens and error.
- Get traces by trace idOne turn with all its spans (every model step and tool call with full input/output).
- Get traces countCount the turns matching the same filters as /traces.
- Get traces summaryWhat one turn did, in a small response.
- Get wallet programmeWhether agent wallets are offered on this deployment.
- Get webhook deliveriesList 50 outgoing consent/test webhook deliveries in this org, newest first.
- Get webhook deliveries by idRead one org-owned outgoing delivery, its immutable event payload and the latest 100 attempts.
- Get webhooksList the org’s webhook endpoints (id, name, url) — the targets an escalation route can post to.
- Get webhooks by idOne webhook endpoint.
- List agent templatesList the agent templates available for deployments.
- List channel typesList the channel types and required deployment fields.
- Post identities slack validateCheck pasted Slack app credentials before storing them.
- Post identities telegram validateResolve a Telegram bot token through getMe and return the bot’s id, username and first name, without persisting anything.
- Post identities whatsapp validateResolve a Meta access token + phone number id to the WhatsApp number they belong to — display number and verified name — plus the webhook…
- Post identities x validate app credentialsCheck that an X app API key + API key secret pair can mint the app-only bearer token that registers the X webhook, without storing anything.
Takes action
- Cancel jobStop a job started by a long call, and ask the work behind it to stop too.
- Delete agent groups by idDelete an agent group, so its members can no longer ask each other through it.
- Delete agents by idDelete an agent with its tools, alerts, loops and configuration, releasing its Keiki VM if it has one.
- Delete agents capabilities by slugUninstall a capability from an agent, dropping its version pin.
- Delete agents identity webhookRemove sender identity checks.
- Delete agents lines by numberRemove a phone line from an agent.
- Delete agents loops by loop idDelete one of the agent’s scheduled loops for good.
- Delete agents mcp presets by preset idDisconnect an MCP preset from the agent and remove it from its daemon.
- Delete agents tools by tool idDelete an authored tool.
- Delete agents wallet intents by intent idRevoke a purchase.
Show 171 more
- Delete conversations blockUnblock one identity for this conversation’s agent so its messages trigger replies again.
- Delete conversations contact cardClear the dynamic contact card for this conversation.
- Delete conversations historyPermanently delete one agent’s stored message history with an identity and return how many messages were cleared.
- Delete conversations takeoverEnd a human takeover early and hand the conversation back to the agent, including any hold taken from a Slack thread.
- Delete deploymentDelete one deployment and release its connected channels.
- Delete evals cases by idDelete an organization eval case permanently, not just archive it.
- Delete identities by idDelete an identity.
- Delete identities slack installs by install idStop answering in one workspace that installed this Slack identity, without touching the app or its other workspaces — the workspace keeps…
- Delete identities slack operators by slack user idRemove one Slack user from a Slack identity’s operator allowlist.
- Delete identities slack teams by team idStop routing one customer Slack workspace to its agent.
- Delete identities teams installs by install idForget one tenant’s install of a Teams identity so the agent stops answering there.
- Delete invitations by idRevoke a pending invitation so its link no longer works.
- Delete mcp clients by token idRevoke this user’s organization OAuth connection.
- Delete members by idRemove a member from the organization.
- Delete org mcp integrations by idStop sharing an org MCP integration, removing it from every agent it was granted to.
- Delete paymentsDisconnect payments.
- Delete payments payees by idDelete a payee.
- Delete provider accounts by idDisconnect one of the organization’s own Photon accounts.
- Delete sandbox scripts by idDelete a sandbox script.
- Delete secrets by nameDelete a secret and its bound mirrors.
- Delete skills by idDelete a skill or document.
- Delete ssoDisable SSO.
- Delete sso domains by idRemove an SSO domain.
- Delete trace exporters by idDelete a destination and its agent attachments.
- Delete webhooks by idDelete a webhook endpoint.
- Deploy agentCreate or update an agent deployment using the body format of POST /api/v1/developer/deployments.
- EscalateFile a bug report or feature request about the Keiki platform itself with the engineering team.
- Get agents executorResolve the agent’s Executor.sh sandbox daemon and return its current short-lived MCP URL, base URL and scope (never its auth token).
- Get billing portalCreate a Stripe billing portal link for the organization.
- Get identities x oauth callbackThe redirect X sends the user back to after authorizing.
- Patch identities group chatPatch a Telegram identity’s group-chat behaviour — only the fields sent change.
- Patch identities phone calls voiceSet a phone line's voice.
- Patch members by idChange one member’s role, or their display name — one or the other per call.
- Patch notificationsUpdate the signed-in user’s daily digest settings.
- Patch orgs currentRename the active organization, change its logo domain, or upload a logo.
- Patch people by person idSet the fields an operator owns on a person, patching only those sent.
- Patch ssoUpdate IdP metadata/configuration and defaultRole, enforce, activate.
- Post agent groupsCreate an agent group, optionally with its members, and return its id.
- Post agent groups endStop a whole group.
- Post agentmail domainsAdd a custom email domain for agent inboxes.
- Post agentsCreate an agent and return its id.
- Post agents a2aTurn the agent’s A2A endpoint and Agent Card on or off.
- Post agents actions decideApprove (run) or decline one pending agent action and return the updated action.
- Post agents actions groups decideApprove or decline every pending action sharing a group id (from GET /agents/.
- Post agents api gatewayTurn the agent’s OpenAI/Anthropic-compatible API on or off, and/or switch passthrough mode (the caller’s own prompt leads each turn) —…
- Post agents by idUpdate an agent from its GET /agents/.
- Post agents capabilitiesInstall a marketplace capability version on an agent, or re-pin an installed one to another version.
- Post agents capabilities enabledEnable or disable an installed capability, keeping its pinned version.
- Post agents evals channel hostedStart a real-channel eval run in which a platform-owned identity messages the agent over a real channel.
- Post agents fine tune startRecord a fine-tune request for the agent’s current version.
- Post agents harness redeployReplace a Maritime agent’s Keiki VM with a fresh one built from the current runner and return the new VM status.
- Post agents harness signing secretRotate an external harness credential.
- Post agents linesGive an agent another phone line.
- Post agents lines moveMove a line this agent holds to another agent in one step.
- Post agents loops clear historyReset a loop.
- Post agents loops enabledPause or resume one of the agent’s scheduled loops.
- Post agents loops runRun one of the agent’s scheduled loops now, through the same pipeline as a scheduled run.
- Post agents mcp presets connectConnect (or reconnect) one MCP preset on the agent’s Executor daemon.
- Post agents mcp presets shareShare an agent’s MCP connection with the organization.
- Post agents mcp presets statusRe-check an MCP preset’s connection on the daemon without restarting OAuth — poll it after the user authorizes.
- Post agents noticeTell the agent something in its own conversations and let it decide whether the people in them hear about it — how you notify everyone…
- Post agents quality applyApply a drafted fix to the agent’s live configuration (a new agent version).
- Post agents quality dismissDismiss a drafted fix, together with the failure cluster it came from so the same symptom is not suggested again.
- Post agents quality settingsChange the agent’s turn-review settings.
- Post agents rollouts percentSet the share of conversations an open rollout serves its staged config to, and resume it when paused.
- Post agents rollouts promoteMake the rollout’s staged config live for every conversation, recorded as a new version, and end the rollout.
- Post agents rollouts rollbackEnd the rollout and send every conversation back to the live config.
- Post agents template importRe-apply the agent’s own template, at the template’s current version, onto its configuration (e.g.
- Post agents toolsSave a new authored code tool as a disabled draft (saving under the name of an existing authored tool rewrites that draft).
- Post agents tools enablePublish an authored tool to the agent so it can call it, or unpublish it with enabled false.
- Post agents versions restoreRoll the agent back to the configuration saved at a version sha, recorded as a new version whose sha is returned.
- Post billing credits purchaseBuy usage credits for the organization.
- Post billing plans attachAttach the selected plan to the organization.
- Post billing release lineRelease an active phone line owned by the organization and unassign it from agents.
- Post channel access requestsSubmit { channel, purpose, expectedVolume }.
- Post conversations blockBlock one identity for this conversation’s agent, so its messages no longer trigger agent replies.
- Post conversations endEnd an inter-agent (agent.
- Post conversations messagesSend a message the contact reads as the agent’s, over the conversation’s own channel, and renew the takeover.
- Post conversations steerRun a turn on this conversation as if the contact had written the text, and return what the agent would answer with its trace id.
- Post conversations takeoverHold one conversation for a human for 30 minutes.
- Post evals casesAdd a user-authored eval case to an agent in the organization and return the saved case.
- Post evals cases generateRe-author and persist the agent’s generated eval suite from its current configuration, keeping user and regression cases and recording a…
- Post evals diffsStart paid-plan evals comparing two different readable config versions of the organization’s agent against up to 12 existing cases.
- Post evals runsStart a paid-plan eval run on the agent’s saved suite, or selected case ids including archived cases.
- Post evals runs cancelRequest cooperative cancellation of an organization eval run that is still running.
- Post evals suggestions createCreate regression eval cases from selected production suggestions by replaying recorded conversation evidence in a mocked world, without…
- Post identities agentmailCreate an AgentMail email identity attached to an agent — a new inbox on the managed domain or one of the org’s verified custom domains,…
- Post identities agentmail reconnectRotate an AgentMail identity’s inbox-scoped API key — mints a replacement, stores it, deletes the old key, and when attached re-registers…
- Post identities agentmail verifyVerify an AgentMail identity.
- Post identities attachRoute an identity to an agent.
- Post identities detachStop routing an identity to its agent.
- Post identities phone callsBuy a voice number in the area code or state (or any US number when neither is given) and connect it to the agent for inbound phone calls…
- Post identities phone calls forwarding requestsAsk the team to set up call forwarding by hand for an iMessage line whose provider cannot do it automatically.
- Post identities phone calls voices previewSpeak a short text (at most 300 characters.
- Post identities slackCreate a Slack identity from a manually-built Slack app.
- Post identities slack install linkMint a signed Slack install link that binds the installing workspace to an agent.
- Post identities slack install links revokeStop every install link made so far for a customer-workspace Slack app, without touching its signing secret.
- Post identities slack operatorsAdd one Slack user to a Slack identity’s operator allowlist without touching the other entries.
- Post identities slack reconnectReplace a Slack identity’s credentials with a fresh bot token for the same Slack app — the token must resolve to the app already connected…
- Post identities slack signing probeStore a candidate Slack signing secret and have the bot post a setup instruction into a channel.
- Post identities slack verifyRe-check every workspace install of a Slack identity against Slack.
- Post identities teamsCreate a Microsoft Teams identity from an Azure Bot registration — the App ID and a client secret are validated by minting a Bot Framework…
- Post identities telegramCreate a Telegram bot identity, optionally attached to an agent.
- Post identities whatsappCreate a WhatsApp Cloud API identity, optionally attached to an agent.
- Post identities whatsapp kapsoConnect { phoneNumberId, agentId?
- Post identities whatsapp kapso ownConnect { apiKey, phoneNumberId, agentId?
- Post identities whatsapp kapso startMint an organization Kapso signup link.
- Post identities xCreate an X account identity for public mentions and direct messages, from a completed “Log in with X” grant.
- Post identities x oauth startStart an X OAuth 2.0 login that mints a refreshable user token for an X identity.
- Post identities x reconnectReplace the authorization of an X identity whose token X revoked, using a completed “Log in with X” for the same account.
- Post invitationsInvite someone to the organization by email.
- Post invitations resendResend a pending invitation with a fresh accept link and a renewed expiry.
- Post keysCreate an API key, optionally bound to a single agent of this organization.
- Post keys revokeRevoke an API key so every later request with it is rejected.
- Post keys rotateRotate an API key.
- Post lines contact cardSet the first and last name iMessage shows for a line, applied through its provider (Photon or Linq) and returned as the saved card.
- Post lines previewQuote a new iMessage line with a coupon applied, without charging, redeeming the coupon or provisioning.
- Post lines purchaseBuy a new iMessage line for the organization from Photon (default) or Blooio, optionally with a coupon and connected straight to an agent.
- Post lines requestAsk the Keiki team for a Linq line.
- Post lines verifyCheck one line’s inbound webhook registration with its provider and its stored routing status.
- Post marketplace mine submitSubmit one of the organization’s own capability versions for marketplace publication review.
- Post marketplace reviews by capability idApprove (publish) or reject a capability that is awaiting review, with an optional note to the publisher.
- Post members transfer ownershipMake another member the owner of the organization.
- Post org mcp integrations syncRe-run the reconciliation of an org MCP integration into every granted agent now, in the background.
- Post payments identity verificationStart payment identity verification.
- Post payments keyConnect Grosso using { apiKey }.
- Post payments liveSwitch payments to live mode.
- Post payments payeesCreate { ownerEmail, agentId, maxAmount, dailyAmount } (integer cents).
- Post payments payees by idAssign a payee with { agentId }.
- Post payments signupStart Grosso signup with { email, name }.
- Post payments verifyVerify signup with { code, acceptTerms.
- Post sandbox scriptsCreate a sandbox script.
- Post skillsCreate a skill or knowledge document — always a new one.
- Post sso domainsRegister { domain }.
- Post sso setup linkCreate a single-use SSO setup credential.
- Post sso testStart an SSO test.
- Post subagent tasks cancelCancel one running or suspended background task an agent delegated.
- Post trace exportersAdd a destination that receives every finished turn of its attached agents.
- Post traces abortAsk a running turn to stop.
- Post traces retryRe-run a failed turn with its original input, or re-run its linked loop.
- Post webhook deliveries resendOwners/admins only.
- Post webhooksCreate a named webhook endpoint.
- Post webhooks signing secretRotate a destination webhook credential.
- Post webhooks testQueue a synthetic webhook delivery.
- Put agent groups by idUpdate an agent group.
- Put agent groups noteReplace the whole group note with a new body and return the new revision.
- Put agents harness connectionConfigure an external harness with { mode.
- Put agents livePause an agent or put it back live.
- Put agents mcp presetsReplace the agent’s whole MCP preset list (at most 10).
- Put agents mcp presets tool permissionsReplace the allow/ask/deny choices for one MCP’s tools and push them to the daemon.
- Put agents noteReplace the whole working note body (read it first to keep what matters) and return the new revision.
- Put agents public profilePublish or unpublish the agent’s public profile page (which shows its name and phone line) and set its tagline.
- Put agents tools by tool idUpdate an authored tool.
- Put agents user connectionsReplace the agent’s personal provider definitions with the list sent (read GET first and keep the providers you are not changing) and…
- Put agents walletUpdate the agent’s wallet, creating it if needed.
- Put billing auto top upTurn auto top-up on or off.
- Put conversations contact cardSet the name, organization, title and optional photo for this conversation’s contact card.
- Put evals cases by idReplace an eval case’s editable fields and adopt it as user-authored so regeneration preserves it.
- Put identities slack events webhookSend a customer-workspace Slack app’s slack.installed, slack.uninstalled and slack.unbound_message events to one of the org’s saved…
- Put identities slack operatorsReplace a Slack identity’s operator allowlist wholesale.
- Put identities slack teams by team idRoute one customer Slack workspace to an agent, replacing any previous binding.
- Put org mcp integrations credentialsReplace the authentication headers of a header-authenticated org MCP integration.
- Put org mcp integrations grantsReplace the full set of groups and agents an org MCP integration is granted to — anything not listed loses access, so read the current…
- Put orgs current build recommendationsReplace the Home ideas the active organization wrote itself.
- Put sandbox scripts by idEdit a sandbox script in place, patching only the fields sent.
- Put secrets by nameStore an encrypted secret with { value }.
- Put skills by idEdit a skill in place, patching only the fields sent.
- Put trace exporters by idUpdate a destination — replaces name, format, endpoint, enabled and agentIds, so read it first and send them all.
- Put webhooks by idUpdate a webhook endpoint — replaces both name and url, so send both.
- Switch organizationList the organizations this account belongs to, or switch this connection to one of them.
- Talk to agentSend one message to one of this organization's agents as a real user, and read what it replies.