# Keiki MCP

Build and manage Keiki agents, conversations, evaluations, channels, billing, integrations, and organization settings through the official hosted MCP server.

Category: Developer. Connect from any Opisense bot at https://www.opisense.com/integrations/keiki-mcp/.

## Actions

- **Cancel job**: Stop a job started by a long call, and ask the work behind it to stop too.
- **Check job** (read-only): Read a job that a long call handed back instead of a result.
- **Current context** (read-only): Who this token acts as, which organization it is bound to, and the current time.
- **Delete agent groups by id**: Delete an agent group, so its members can no longer ask each other through it.
- **Delete agents by id**: Delete an agent with its tools, alerts, loops and configuration, releasing its Keiki VM if it has one.
- **Delete agents capabilities by slug**: Uninstall a capability from an agent, dropping its version pin.
- **Delete agents identity webhook**: Remove sender identity checks.
- **Delete agents lines by number**: Remove a phone line from an agent.
- **Delete agents loops by loop id**: Delete one of the agent’s scheduled loops for good.
- **Delete agents mcp presets by preset id**: Disconnect an MCP preset from the agent and remove it from its daemon.
- **Delete agents tools by tool id**: Delete an authored tool.
- **Delete agents wallet intents by intent id**: Revoke a purchase.
- **Delete conversations block**: Unblock one identity for this conversation’s agent so its messages trigger replies again.
- **Delete conversations contact card**: Clear the dynamic contact card for this conversation.
- **Delete conversations history**: Permanently delete one agent’s stored message history with an identity and return how many messages were cleared.
- **Delete conversations takeover**: End a human takeover early and hand the conversation back to the agent, including any hold taken from a Slack thread.
- **Delete deployment**: Delete one deployment and release its connected channels.
- **Delete evals cases by id**: Delete an organization eval case permanently, not just archive it.
- **Delete identities by id**: Delete an identity.
- **Delete identities slack installs by install id**: Stop 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 id**: Remove one Slack user from a Slack identity’s operator allowlist.
- **Delete identities slack teams by team id**: Stop routing one customer Slack workspace to its agent.
- **Delete identities teams installs by install id**: Forget one tenant’s install of a Teams identity so the agent stops answering there.
- **Delete invitations by id**: Revoke a pending invitation so its link no longer works.
- **Delete mcp clients by token id**: Revoke this user’s organization OAuth connection.
- **Delete members by id**: Remove a member from the organization.
- **Delete org mcp integrations by id**: Stop sharing an org MCP integration, removing it from every agent it was granted to.
- **Delete payments**: Disconnect payments.
- **Delete payments payees by id**: Delete a payee.
- **Delete provider accounts by id**: Disconnect one of the organization’s own Photon accounts.
- **Delete sandbox scripts by id**: Delete a sandbox script.
- **Delete secrets by name**: Delete a secret and its bound mirrors.
- **Delete skills by id**: Delete a skill or document.
- **Delete sso**: Disable SSO.
- **Delete sso domains by id**: Remove an SSO domain.
- **Delete trace exporters by id**: Delete a destination and its agent attachments.
- **Delete webhooks by id**: Delete a webhook endpoint.
- **Deploy agent**: Create or update an agent deployment using the body format of POST /api/v1/developer/deployments.
- **Escalate**: File a bug report or feature request about the Keiki platform itself with the engineering team.
- **Get agent goals** (read-only): The outcome kinds each agent has produced and whether any carry money — what an agent’s CRM columns stand for.
- **Get agent groups** (read-only): List 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 activity** (read-only): Every 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 note** (read-only): The group’s shared note — what its agents have settled among themselves (decisions, who does what, findings) — with its revision, last…
- **Get agent groups note versions** (read-only): History of the group note, newest first.
- **Get agent groups note versions by sha** (read-only): The group note body as it was at one historical version (a sha from the versions list).
- **Get agent groups roster** (read-only): Live roster of one group.
- **Get agent groups threads** (read-only): The asker→peer threads currently live among one group’s members (who is asking whom right now).
- **Get agent templates** (read-only): Complete agent templates the platform can provision in one call (e.g.
- **Get agentmail domains** (read-only): Custom email domains the organization added for agent inboxes, each with its region and live DNS verification state from AgentMail.
- **Get agents** (read-only): List every agent in the organization with its status, model and channels.
- **Get agents a2a** (read-only): Whether other vendors’ agents can call the agent over A2A, with its Agent Card URL and JSON-RPC endpoint.
- **Get agents actions** (read-only): List the agent’s persisted approval actions (tool calls waiting on, or past, a human decision), newest first, with their status, arguments…
- **Get agents analytics** (read-only): Engagement for one agent over a date range.
- **Get agents api gateway** (read-only): Whether 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 id** (read-only): Agent detail.
- **Get agents capabilities** (read-only): List the marketplace capabilities installed on an agent, including disabled ones, with each pinned version, how it was installed, any…
- **Get agents conversations** (read-only): Every 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 phone** (read-only): One conversation thread between the agent and a contact (phone is their phone number, email or tg.
- **Get agents conversations sentiment** (read-only): One conversation’s mood per user turn, oldest first (0 angry to 4 delighted.
- **Get agents edit** (read-only): The agent form payload.
- **Get agents evals channel preview** (read-only): Preview a real-channel eval run per hosted driver (imessage, email, x).
- **Get agents executor**: Resolve the agent’s Executor.sh sandbox daemon and return its current short-lived MCP URL, base URL and scope (never its auth token).
- **Get agents fine tune** (read-only): Read fine-tune readiness for the agent’s current version.
- **Get agents harness status** (read-only): Report what runs the agent and whether it is connected.
- **Get agents loops** (read-only): List the scheduled loops attached to an agent with their schedule and state.
- **Get agents loops runs** (read-only): Read a loop’s recent runs, newest first, from a bounded retention window.
- **Get agents mcp presets tools** (read-only): The tools a connected MCP exposes, read live from the daemon, each with the permission (allow/ask/deny) in force, plus the default…
- **Get agents note** (read-only): Read the agent’s working note — the durable scratchpad it rewrites while it works — with its revision.
- **Get agents note versions** (read-only): List the working note’s version history, newest first, with the sha of each version.
- **Get agents note versions by sha** (read-only): Read the working note body as it was at one version sha from the history.
- **Get agents public profile** (read-only): Whether the agent’s public profile page is published, its URL slug and tagline, and whether the caller may change it.
- **Get agents quality** (read-only): Turn-quality review for one agent.
- **Get agents rollouts** (read-only): Read 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 runs** (read-only): The latest 50 runs of the agent’s sandbox scripts, newest first — status, exit code and output tails.
- **Get agents shared line** (read-only): The shared iMessage number and join code contacts text to reach this agent.
- **Get agents signals** (read-only): Built-in quality signals for one agent over a date range.
- **Get agents signals events** (read-only): The turns one signal (key, as returned by the signals summary) fired on, newest first.
- **Get agents user connections** (read-only): List the personal provider definitions declared on the agent — services each conversation user authorizes with their own account.
- **Get agents versions** (read-only): List the agent configuration’s version history, with the sha of each version.
- **Get agents versions by sha** (read-only): Read the agent configuration snapshot saved at one version sha.
- **Get agents wallet** (read-only): The agent’s wallet.
- **Get agents wallet payment methods** (read-only): Labelled payment methods on the wallet’s connected account (never card numbers), for choosing paymentMethodId.
- **Get audit** (read-only): List audit events as { events, nextCursor }.
- **Get audit verify** (read-only): Verify the organization audit hash chain and return its verification result.
- **Get auto** (read-only): Read whether the organization’s plan allows Auto mode and which front and worker models it uses.
- **Get axiom traces** (read-only): Spans read from the OTLP collector — kept past the 14-day window of /traces, and alongside spans other services exported under the same…
- **Get billing** (read-only): Read the organization’s billing overview.
- **Get billing activity** (read-only): List the organization’s invoice and platform credit grant activity, newest first.
- **Get billing auto top up** (read-only): Read the organization’s auto top-up settings.
- **Get billing capability pricing** (read-only): Read the default plan’s per-capability billing metadata, included amounts, units and price labels.
- **Get billing capability usage by agent** (read-only): Read local capability usage grouped by feature and agent for each feature’s latest recorded billing period, including unattributed and…
- **Get billing consumer pricing** (read-only): Read public consumer plans, add-ons and feature pricing metadata from the billing catalog.
- **Get billing included allowance** (read-only): Read public default-plan included token-credit allowances without customer data.
- **Get billing plans** (read-only): List the organization’s available non-add-on, non-archived plans with display prices, features, trial information and current/scheduled…
- **Get billing portal**: Create a Stripe billing portal link for the organization.
- **Get billing pricing account** (read-only): Read the connected organization’s current plan and status, usage and credit access checks.
- **Get billing public plans** (read-only): Read public recurring plans with included limits and platform credit conversion rates for comparing options.
- **Get billing service spend** (read-only): Read the organization’s recorded customer service charges for the billing period.
- **Get billing status** (read-only): Check the organization’s lightweight plan gate rather than loading its billing overview.
- **Get billing usage by conversation** (read-only): List up to 100 conversations with the most recorded token usage across the organization’s active developer configurations, excluding…
- **Get blog** (read-only): Keiki's own blog, newest first.
- **Get blog by slug** (read-only): One Keiki blog post in full.
- **Get capability tools** (read-only): Every 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 requests** (read-only): List organization early-access requests as { requests }.
- **Get conversations** (read-only): One page of the organization’s conversations, most recent first, each with its agent, identity and latest state.
- **Get conversations by phone** (read-only): One conversation thread by identity (phone number, email, or prefixed id like tg.
- **Get conversations contact card** (read-only): Read the contact card set specifically for this conversation, and whether dynamic contact cards are available.
- **Get conversations count** (read-only): How many conversations match the same filters as the conversation list, and how many of those need a person.
- **Get dashboard** (read-only): Home-page summary for the signed-in user.
- **Get deployment** (read-only): Read one deployment in the current organization.
- **Get evals cases** (read-only): List the organization agent’s persisted eval cases, including generated, user-authored and regression cases.
- **Get evals cases versions** (read-only): Read the generated eval suite’s version history for an agent in the organization.
- **Get evals diffs** (read-only): Compare two organization eval runs as their results arrive.
- **Get evals runs by id** (read-only): Read one organization eval run’s status, candidates, rankings and per-case results with trace ids.
- **Get evals runs cases** (read-only): Read the full persisted case records referenced by an organization eval run, including archived cases.
- **Get evals runs latest** (read-only): Read the agent’s latest eval run, optionally limited to single-model, sweep or real-channel runs.
- **Get evals runs transcript** (read-only): Read an organization real-channel eval run’s recorded message transcript.
- **Get evals suggestions** (read-only): Find behaviors worth testing from the agent’s recorded production traffic in the chosen window, with trace counts, error rates, models and…
- **Get identities** (read-only): List 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 lines** (read-only): List the agent's iMessage lines and whether each can forward its calls.
- **Get identities phone calls numbers** (read-only): Search 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 voices** (read-only): List the ElevenLabs voices a phone line can use.
- **Get identities slack channels** (read-only): Per 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 manifest** (read-only): Build 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 operators** (read-only): List 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 id** (read-only): Check a Slack signing-secret probe.
- **Get identities slack teams** (read-only): For a Slack app that routes customer workspaces to different agents, list each workspace.
- **Get identities teams manifest** (read-only): The Teams app manifest for a connected Teams identity — it names that identity’s Microsoft App ID.
- **Get identities teams setup** (read-only): Return the messaging endpoint an Azure Bot registration must point at before a Teams identity can be connected.
- **Get identities whatsapp kapso available** (read-only): Read platform Kapso configuration as { available }.
- **Get identities x oauth available** (read-only): Whether “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 callback**: The redirect X sends the user back to after authorizing.
- **Get identities x oauth status** (read-only): Poll a started X login.
- **Get insights** (read-only): Org analytics over a date range.
- **Get invitations** (read-only): List the organization’s invitations, newest first, with email, role, status (pending, accepted or revoked) and expiry.
- **Get keys** (read-only): List the organization’s API keys.
- **Get keys usage** (read-only): Daily usage of one API key, aggregated by day, by route and method, and by agent, with accepted vs rejected (revoked/expired) counts and…
- **Get lines** (read-only): List 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 card** (read-only): Read 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 price** (read-only): The display price of a new iMessage line (price, e.g.
- **Get lines providers** (read-only): Status of each iMessage line provider (Photon, Linq, Blooio) as shown on the status page.
- **Get lines provisioning by id** (read-only): Progress of one of the organization’s line purchases.
- **Get live snapshot** (read-only): What the org’s agents are doing right now.
- **Get loops** (read-only): List the organization’s scheduled loops, newest first.
- **Get marketplace capabilities** (read-only): Browse published (reviewed) marketplace capabilities, one listing per capability with its newest version and the other versions available…
- **Get marketplace mine** (read-only): List the capabilities this organization has published itself, in every review state (draft, pending review, published, rejected).
- **Get marketplace reviews** (read-only): List the capabilities awaiting publication review.
- **Get mcp brand lookup** (read-only): Resolve the brand behind an MCP server endpoint URL — its name, domain, description and logo.
- **Get mcp catalog** (read-only): Search the approved integrations.sh catalog of connectable services (name, domain, description, kind, icon, categories).
- **Get mcp catalog by domain** (read-only): Resolve one catalogued domain into its connectable surfaces — MCP endpoints, OpenAPI/GraphQL specs and CLIs — with each surface’s URL,…
- **Get mcp clients** (read-only): List this user’s organization OAuth connections as { connections }.
- **Get members** (read-only): List 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 models** (read-only): Search the models an agent can run on — ids, context window, price per million tokens, and tool, reasoning and vision support.
- **Get notifications** (read-only): The signed-in user’s daily digest preference (digestOptOut) and the timezone the digest is sent in (null when none was reported).
- **Get org mcp integrations** (read-only): List the organization-owned MCP integrations.
- **Get orgs** (read-only): List 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 logo** (read-only): Look up the brand logo URL for a domain.
- **Get orgs current** (read-only): Read the active organization’s id, name, logo domain and logo URL, and whether the caller may edit it (canManage).
- **Get orgs current build recommendations** (read-only): Read the agent ideas Home shows for the active organization.
- **Get outcomes** (read-only): Recorded business outcomes — sales, bookings, qualified leads — newest first, with totals per kind for the same agent, person and time…
- **Get payments** (read-only): Read the organization’s Grosso payments account.
- **Get payments payees** (read-only): Read the organization’s newest 100 Grosso payees (businesses it collects payments for).
- **Get people** (read-only): Directory of the people behind the organization’s conversations, most recently seen first, with the total matching count.
- **Get people by person id** (read-only): One person.
- **Get provider accounts** (read-only): List the organization’s own Photon accounts connected to Keiki.
- **Get sandbox providers** (read-only): Read sandbox provider availability as { providers }.
- **Get sandbox scripts** (read-only): List 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 id** (read-only): Read one sandbox script, including its body, targets, timeout and env secret names.
- **Get sandbox scripts runs** (read-only): Every sandbox run of one script across its agents, newest first — status, exit code and output tails.
- **Get sandbox scripts versions** (read-only): Version history of a sandbox script, newest first — each entry carries the commit sha to read it at.
- **Get sandbox scripts versions by sha** (read-only): Read a sandbox script’s body as of one version, by the sha from its version history.
- **Get secrets** (read-only): List the organization’s developer secret names with created/updated times and any host binding.
- **Get signals** (read-only): Built-in quality signals across every agent in the org, or one agent.
- **Get skills** (read-only): List the org’s skills and knowledge documents (metadata, no body) with the agents each is attached to.
- **Get skills by id** (read-only): Read one skill or document, including its full body.
- **Get skills presets** (read-only): List the built-in preset skills (id, capability, name, description, kind) and whether the org already added each.
- **Get skills versions** (read-only): Version history of a skill, newest first — each entry carries the commit sha to read it at.
- **Get skills versions by sha** (read-only): Read a skill’s body and metadata as of one version, by the sha from its version history.
- **Get sso** (read-only): Read SSO connection, domains, eligibility and platform configuration.
- **Get trace exporters** (read-only): List the destinations the org ships finished turns to — format, endpoint, header names (never values), enabled, attached agent ids, last…
- **Get traces** (read-only): List one page of the org’s agent turns (traces), newest first, with status, model, tokens and error.
- **Get traces by trace id** (read-only): One turn with all its spans (every model step and tool call with full input/output).
- **Get traces count** (read-only): Count the turns matching the same filters as /traces.
- **Get traces summary** (read-only): What one turn did, in a small response.
- **Get wallet programme** (read-only): Whether agent wallets are offered on this deployment.
- **Get webhook deliveries** (read-only): List 50 outgoing consent/test webhook deliveries in this org, newest first.
- **Get webhook deliveries by id** (read-only): Read one org-owned outgoing delivery, its immutable event payload and the latest 100 attempts.
- **Get webhooks** (read-only): List the org’s webhook endpoints (id, name, url) — the targets an escalation route can post to.
- **Get webhooks by id** (read-only): One webhook endpoint.
- **List agent templates** (read-only): List the agent templates available for deployments.
- **List channel types** (read-only): List the channel types and required deployment fields.
- **Patch identities group chat**: Patch a Telegram identity’s group-chat behaviour — only the fields sent change.
- **Patch identities phone calls voice**: Set a phone line's voice.
- **Patch members by id**: Change one member’s role, or their display name — one or the other per call.
- **Patch notifications**: Update the signed-in user’s daily digest settings.
- **Patch orgs current**: Rename the active organization, change its logo domain, or upload a logo.
- **Patch people by person id**: Set the fields an operator owns on a person, patching only those sent.
- **Patch sso**: Update IdP metadata/configuration and defaultRole, enforce, activate.
- **Post agent groups**: Create an agent group, optionally with its members, and return its id.
- **Post agent groups end**: Stop a whole group.
- **Post agentmail domains**: Add a custom email domain for agent inboxes.
- **Post agents**: Create an agent and return its id.
- **Post agents a2a**: Turn the agent’s A2A endpoint and Agent Card on or off.
- **Post agents actions decide**: Approve (run) or decline one pending agent action and return the updated action.
- **Post agents actions groups decide**: Approve or decline every pending action sharing a group id (from GET /agents/.
- **Post agents api gateway**: Turn 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 id**: Update an agent from its GET /agents/.
- **Post agents capabilities**: Install a marketplace capability version on an agent, or re-pin an installed one to another version.
- **Post agents capabilities enabled**: Enable or disable an installed capability, keeping its pinned version.
- **Post agents evals channel hosted**: Start a real-channel eval run in which a platform-owned identity messages the agent over a real channel.
- **Post agents fine tune start**: Record a fine-tune request for the agent’s current version.
- **Post agents harness redeploy**: Replace 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 secret**: Rotate an external harness credential.
- **Post agents lines**: Give an agent another phone line.
- **Post agents lines move**: Move a line this agent holds to another agent in one step.
- **Post agents loops clear history**: Reset a loop.
- **Post agents loops enabled**: Pause or resume one of the agent’s scheduled loops.
- **Post agents loops run**: Run one of the agent’s scheduled loops now, through the same pipeline as a scheduled run.
- **Post agents mcp presets connect**: Connect (or reconnect) one MCP preset on the agent’s Executor daemon.
- **Post agents mcp presets share**: Share an agent’s MCP connection with the organization.
- **Post agents mcp presets status**: Re-check an MCP preset’s connection on the daemon without restarting OAuth — poll it after the user authorizes.
- **Post agents notice**: Tell 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 apply**: Apply a drafted fix to the agent’s live configuration (a new agent version).
- **Post agents quality dismiss**: Dismiss a drafted fix, together with the failure cluster it came from so the same symptom is not suggested again.
- **Post agents quality settings**: Change the agent’s turn-review settings.
- **Post agents rollouts percent**: Set the share of conversations an open rollout serves its staged config to, and resume it when paused.
- **Post agents rollouts promote**: Make the rollout’s staged config live for every conversation, recorded as a new version, and end the rollout.
- **Post agents rollouts rollback**: End the rollout and send every conversation back to the live config.
- **Post agents template import**: Re-apply the agent’s own template, at the template’s current version, onto its configuration (e.g.
- **Post agents tools**: Save a new authored code tool as a disabled draft (saving under the name of an existing authored tool rewrites that draft).
- **Post agents tools enable**: Publish an authored tool to the agent so it can call it, or unpublish it with enabled false.
- **Post agents versions restore**: Roll the agent back to the configuration saved at a version sha, recorded as a new version whose sha is returned.
- **Post billing credits purchase**: Buy usage credits for the organization.
- **Post billing plans attach**: Attach the selected plan to the organization.
- **Post billing release line**: Release an active phone line owned by the organization and unassign it from agents.
- **Post channel access requests**: Submit { channel, purpose, expectedVolume }.
- **Post conversations block**: Block one identity for this conversation’s agent, so its messages no longer trigger agent replies.
- **Post conversations end**: End an inter-agent (agent.
- **Post conversations messages**: Send a message the contact reads as the agent’s, over the conversation’s own channel, and renew the takeover.
- **Post conversations steer**: Run 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 takeover**: Hold one conversation for a human for 30 minutes.
- **Post evals cases**: Add a user-authored eval case to an agent in the organization and return the saved case.
- **Post evals cases generate**: Re-author and persist the agent’s generated eval suite from its current configuration, keeping user and regression cases and recording a…
- **Post evals diffs**: Start paid-plan evals comparing two different readable config versions of the organization’s agent against up to 12 existing cases.
- **Post evals runs**: Start a paid-plan eval run on the agent’s saved suite, or selected case ids including archived cases.
- **Post evals runs cancel**: Request cooperative cancellation of an organization eval run that is still running.
- **Post evals suggestions create**: Create regression eval cases from selected production suggestions by replaying recorded conversation evidence in a mocked world, without…
- **Post identities agentmail**: Create 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 reconnect**: Rotate 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 verify**: Verify an AgentMail identity.
- **Post identities attach**: Route an identity to an agent.
- **Post identities detach**: Stop routing an identity to its agent.
- **Post identities phone calls**: Buy 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 requests**: Ask the team to set up call forwarding by hand for an iMessage line whose provider cannot do it automatically.
- **Post identities phone calls voices preview**: Speak a short text (at most 300 characters.
- **Post identities slack**: Create a Slack identity from a manually-built Slack app.
- **Post identities slack install link**: Mint a signed Slack install link that binds the installing workspace to an agent.
- **Post identities slack install links revoke**: Stop every install link made so far for a customer-workspace Slack app, without touching its signing secret.
- **Post identities slack operators**: Add one Slack user to a Slack identity’s operator allowlist without touching the other entries.
- **Post identities slack reconnect**: Replace 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 probe**: Store a candidate Slack signing secret and have the bot post a setup instruction into a channel.
- **Post identities slack validate** (read-only): Check pasted Slack app credentials before storing them.
- **Post identities slack verify**: Re-check every workspace install of a Slack identity against Slack.
- **Post identities teams**: Create 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 telegram**: Create a Telegram bot identity, optionally attached to an agent.
- **Post identities telegram validate** (read-only): Resolve a Telegram bot token through getMe and return the bot’s id, username and first name, without persisting anything.
- **Post identities whatsapp**: Create a WhatsApp Cloud API identity, optionally attached to an agent.
- **Post identities whatsapp kapso**: Connect { phoneNumberId, agentId?
- **Post identities whatsapp kapso own**: Connect { apiKey, phoneNumberId, agentId?
- **Post identities whatsapp kapso start**: Mint an organization Kapso signup link.
- **Post identities whatsapp validate** (read-only): Resolve 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**: Create an X account identity for public mentions and direct messages, from a completed “Log in with X” grant.
- **Post identities x oauth start**: Start an X OAuth 2.0 login that mints a refreshable user token for an X identity.
- **Post identities x reconnect**: Replace the authorization of an X identity whose token X revoked, using a completed “Log in with X” for the same account.
- **Post identities x validate app credentials** (read-only): Check 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.
- **Post invitations**: Invite someone to the organization by email.
- **Post invitations resend**: Resend a pending invitation with a fresh accept link and a renewed expiry.
- **Post keys**: Create an API key, optionally bound to a single agent of this organization.
- **Post keys revoke**: Revoke an API key so every later request with it is rejected.
- **Post keys rotate**: Rotate an API key.
- **Post lines contact card**: Set 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 preview**: Quote a new iMessage line with a coupon applied, without charging, redeeming the coupon or provisioning.
- **Post lines purchase**: Buy a new iMessage line for the organization from Photon (default) or Blooio, optionally with a coupon and connected straight to an agent.
- **Post lines request**: Ask the Keiki team for a Linq line.
- **Post lines verify**: Check one line’s inbound webhook registration with its provider and its stored routing status.
- **Post marketplace mine submit**: Submit one of the organization’s own capability versions for marketplace publication review.
- **Post marketplace reviews by capability id**: Approve (publish) or reject a capability that is awaiting review, with an optional note to the publisher.
- **Post members transfer ownership**: Make another member the owner of the organization.
- **Post org mcp integrations sync**: Re-run the reconciliation of an org MCP integration into every granted agent now, in the background.
- **Post payments identity verification**: Start payment identity verification.
- **Post payments key**: Connect Grosso using { apiKey }.
- **Post payments live**: Switch payments to live mode.
- **Post payments payees**: Create { ownerEmail, agentId, maxAmount, dailyAmount } (integer cents).
- **Post payments payees by id**: Assign a payee with { agentId }.
- **Post payments signup**: Start Grosso signup with { email, name }.
- **Post payments verify**: Verify signup with { code, acceptTerms.
- **Post sandbox scripts**: Create a sandbox script.
- **Post skills**: Create a skill or knowledge document — always a new one.
- **Post sso domains**: Register { domain }.
- **Post sso setup link**: Create a single-use SSO setup credential.
- **Post sso test**: Start an SSO test.
- **Post subagent tasks cancel**: Cancel one running or suspended background task an agent delegated.
- **Post trace exporters**: Add a destination that receives every finished turn of its attached agents.
- **Post traces abort**: Ask a running turn to stop.
- **Post traces retry**: Re-run a failed turn with its original input, or re-run its linked loop.
- **Post webhook deliveries resend**: Owners/admins only.
- **Post webhooks**: Create a named webhook endpoint.
- **Post webhooks signing secret**: Rotate a destination webhook credential.
- **Post webhooks test**: Queue a synthetic webhook delivery.
- **Put agent groups by id**: Update an agent group.
- **Put agent groups note**: Replace the whole group note with a new body and return the new revision.
- **Put agents harness connection**: Configure an external harness with { mode.
- **Put agents live**: Pause an agent or put it back live.
- **Put agents mcp presets**: Replace the agent’s whole MCP preset list (at most 10).
- **Put agents mcp presets tool permissions**: Replace the allow/ask/deny choices for one MCP’s tools and push them to the daemon.
- **Put agents note**: Replace the whole working note body (read it first to keep what matters) and return the new revision.
- **Put agents public profile**: Publish or unpublish the agent’s public profile page (which shows its name and phone line) and set its tagline.
- **Put agents tools by tool id**: Update an authored tool.
- **Put agents user connections**: Replace the agent’s personal provider definitions with the list sent (read GET first and keep the providers you are not changing) and…
- **Put agents wallet**: Update the agent’s wallet, creating it if needed.
- **Put billing auto top up**: Turn auto top-up on or off.
- **Put conversations contact card**: Set the name, organization, title and optional photo for this conversation’s contact card.
- **Put evals cases by id**: Replace an eval case’s editable fields and adopt it as user-authored so regeneration preserves it.
- **Put identities slack events webhook**: Send 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 operators**: Replace a Slack identity’s operator allowlist wholesale.
- **Put identities slack teams by team id**: Route one customer Slack workspace to an agent, replacing any previous binding.
- **Put org mcp integrations credentials**: Replace the authentication headers of a header-authenticated org MCP integration.
- **Put org mcp integrations grants**: Replace 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 recommendations**: Replace the Home ideas the active organization wrote itself.
- **Put sandbox scripts by id**: Edit a sandbox script in place, patching only the fields sent.
- **Put secrets by name**: Store an encrypted secret with { value }.
- **Put skills by id**: Edit a skill in place, patching only the fields sent.
- **Put trace exporters by id**: Update a destination — replaces name, format, endpoint, enabled and agentIds, so read it first and send them all.
- **Put webhooks by id**: Update a webhook endpoint — replaces both name and url, so send both.
- **Switch organization**: List the organizations this account belongs to, or switch this connection to one of them.
- **Talk to agent**: Send one message to one of this organization's agents as a real user, and read what it replies.
