Duvo MCP

List the memory files stored for an agent.

Get the contents of a single memory file for an agent.

List plugins that can be referenced by name in a build's plugins array. Builds may also reference any public GitHub repository URL (https://github.com/owner/repo) as a plugin; those are not enumerated…

Create a schedule for an agent. The schedule fires against the agent's live build. The authenticated user owns the schedule.

Update fields on an existing schedule. Only supplied fields are changed; omitted fields retain their current values. Owners may update their own schedules; team superadmins may update any schedule on …

Delete a schedule. Owners may delete their own schedules; team superadmins may delete any schedule on agents in the current team.

Get a team by ID. The caller must be scoped to the requested team.

Start an OAuth-based connection with a native provider (Gmail, Google Sheets, Outlook, etc.). Returns an authorization URL that must be opened in a browser by a human end-user; once they grant consent…

Start an OAuth-based connection with a remote MCP server using Dynamic Client Registration. Returns an authorization URL the user must open in a browser; once they grant consent, Duvo creates the matc…

Probe an MCP server URL to discover whether it supports OAuth Dynamic Client Registration. Returns the authorization endpoint and required scopes when supported. Useful as a precursor to `/v2/teams/:t…

List your Duvo Pulse dashboards (live, agent-generated visualizations of your Duvo data). Ordered most recently updated first, except scope=automation, which is ordered by creation time (then id) so t…

Create a new Duvo Pulse dashboard from a natural-language prompt (e.g. 'open cases by queue this week') and dispatch the first generation turn. Generation is asynchronous — poll GET /artifacts/{artifa…

Get a Duvo Pulse dashboard's metadata and generation status. When status is completed and html_code_present is true, fetch the rendered HTML from GET /artifacts/{artifactId}/render; the conversation i…

Serve a Duvo Pulse dashboard's rendered HTML document (text/html, not JSON). 404 until the first generation turn has produced HTML.

Render a Duvo Pulse dashboard to a PDF document (application/pdf, not JSON). 404 until the first generation turn has produced HTML; 409 for an openui dashboard, whose substrate this exporter cannot re…

Render a Duvo Pulse dashboard to a self-contained static HTML snapshot (text/html, data baked in). 404 until the first generation turn has produced HTML; 409 for an openui dashboard, whose substrate t…

Update a Duvo Pulse dashboard's settings — rename it. Only the creator can update it.

Publish (share) a Duvo Pulse dashboard to your whole team or your whole organization, or revert it to private (creator only). When publishing, set permission to 'view' (teammates see the dashboard) or…

Delete a Duvo Pulse dashboard. Only the creator can delete it.

Duplicate a Duvo Pulse dashboard, producing an idle clone of the current rendered dashboard. The conversation history, shares, and connections are not copied.

Send an instruction to iterate on a Duvo Pulse dashboard (e.g. 'make it a bar chart', 'filter to last 14 days'). The creator can always iterate; teammates can too when the Pulse is published to the te…

Issue a presigned upload URL for a file to attach to a Duvo Pulse dashboard message (e.g. an HTML dashboard to copy, or a screenshot to match). POST the file bytes to the returned upload_url as multip…

Mint a short-lived presigned URL to download or preview a file attached to a Duvo Pulse dashboard message. Returns 404 once the dashboard's sandbox has expired and the file is gone (about 12 hours).

Trigger an on-demand data refresh of a Duvo Pulse dashboard. The dashboard regenerates its connection-sourced values in the background — poll GET /artifacts/{artifactId} for status.

Stop an in-flight Duvo Pulse generation turn. Requires edit access to the dashboard. Flips the dashboard to 'interrupted' and keeps any streamed-so-far reply; stopping when nothing is generating is a …

List the connections (data sources) attached to a Duvo Pulse dashboard (requires edit access).

Attach one of your connections (data sources) to a Duvo Pulse dashboard so the agent can use its tools (requires edit access).

Detach a connection (data source) from a Duvo Pulse dashboard (requires edit access).

Answer a pending question the Duvo Pulse agent asked and resume the paused run (creator or team editors). Use the toolCallId from the dashboard's message transcript.

List the chat transcript of a Duvo Pulse dashboard's live version (requires edit access). Returns the most recent page by default, oldest first within the page; pass `before` (a message id from a prev…

List the comment threads on a Duvo Pulse dashboard (requires view access). Each thread carries its author, the dashboard element it is pinned to, its replies oldest-first, and whether it has been mark…

Start a comment thread on a Duvo Pulse dashboard (requires view access). Pass `element` — captured from the dashboard canvas — to pin the thread to one element; omit it for a comment on the dashboard …

Reply to a comment thread on a Duvo Pulse dashboard (requires view access). `commentId` must be a thread root; threads are one level deep. A thread already marked complete still accepts replies and st…

Mark a Duvo Pulse dashboard comment thread complete, or reopen it (requires view access). Pass the target state in `resolved`; the call is idempotent, and the response carries the thread with `resolve…

Delete a comment or reply on a Duvo Pulse dashboard. Allowed for the comment's author and for the dashboard's creator. Deleting a thread root keeps its replies, rendered under a deleted opening commen…

List the version history of a Duvo Pulse dashboard, newest first (requires edit access). Use the version id with the restore and version-render endpoints.

Serve a specific version's rendered HTML document for a Duvo Pulse dashboard (text/html, requires edit access).

Restore a previous version of a Duvo Pulse dashboard, making it live again (requires edit access). Non-destructive — it moves the head pointer to the chosen version.

Create a new sandbox for file uploads. The returned sandbox_id can be passed to POST /v2/teams/:team_id/runs to stage data for a run.

Get a presigned URL for uploading a file into a sandbox. Use for files larger than 10MB; smaller files can be uploaded directly via POST /v2/sandboxes/:sandbox_id/files.

List files in a sandbox directory.

Upload a file directly to the sandbox. Maximum file size is 10MB. For larger files, use POST /v2/sandboxes/:sandbox_id/upload-urls.

Get the latest evaluation analysis for a specific agent run (Run).

Aggregate evaluation counts and flag distribution for an Assignment's Jobs since the given timestamp.

List the evaluation rubrics a Run is scored against: the platform default rubrics plus the Agent-specific rubrics for a build. Defaults to the Agent's live build; pass build_id to target the revision …

Add one Agent-specific evaluation rubric to a build. A build may hold at most 5 custom rubrics; this fails with 409 once that ceiling is reached. Defaults to the Agent's live build; pass build_id to t…

Replace a build's entire Agent-specific evaluation rubric set in one call (at most 5 rubrics). Existing custom rubrics are removed and the supplied list becomes the new set; pass an empty array to cle…

Edit a single Agent-specific evaluation rubric's title and/or description. The edit produces a NEW rubric (with a new id and slug) so previously scored Runs stay attributed to the original criterion; …

Remove a single Agent-specific evaluation rubric. Future Runs on the build are no longer scored against it.

List all schedules configured for an agent. Returns the schedules you own on this agent.

List the case triggers configured for an agent. Each trigger automatically dispatches the agent to run cases added to a queue.

Preview which other agents would conflict with this agent's case trigger if it pointed at the given queue. Does not modify the trigger.

Retrieve a single case trigger by id.

Create a case trigger for an agent. An agent may have at most one case trigger; this returns 409 if one already exists.

Update fields on a case trigger. Only the trigger creator or a builder/admin can disable an enabled trigger or change its queue, and only a builder/admin can change queue concurrency.

Delete a case trigger. Only the trigger creator or a builder/admin can delete it.

List the trigger definitions the authenticated user owns on an agent (Agent in the Duvo UI). Triggers start a Run automatically when an external event fires (e.g. an email arrives or a Linear issue is…

Create or update the authenticated user's trigger for an integration on an agent. The integration must already be connected to the agent (its OAuth connection set up in the Duvo dashboard). Set `enabl…

Permanently delete one of your own event triggers on an agent. The agent stops starting Runs for that event and the trigger's filter config is lost. To keep the trigger but stop it firing, upsert it w…

List the trigger types available for an agent, grouped by integration. Use the returned `integration_slug` and `trigger_type` values when creating a trigger.

Create a Slack channel trigger on an agent (Agent in the Duvo UI): the agent starts a Run whenever a matching message is posted in the channel. An agent can carry one trigger per channel, so call this…

List the Slack channel triggers you own on an agent (Agent in the Duvo UI), oldest first. Each trigger's `filter_config` carries the watched `channelId`, `channelName`, Slack `workspaceId`, and `match…

Update a Slack channel trigger you own — repoint it at another channel, change which messages match, or pause and resume it with `enabled`. Only the supplied fields change. Resuming a paused trigger r…

List the Slack workspaces bound to an agent build that you can create channel triggers for. Creating a Slack channel trigger for any other workspace is rejected, so start here to pick a valid `slack_t…

Permanently delete a Slack channel trigger you own. The agent stops starting Runs for that channel. To keep the trigger but stop it firing, update it with `enabled: false` instead.

Create a new revision for an existing agent.

Get a revision by ID.

List revisions for an agent.

Update a revision's configuration, name, description, or handover targets. Returns the updated revision.

Promote a draft or historic revision to the live version. The live revision is the one used by triggers and new runs. Fails if the revision is already live, or if a draft revision still has an active …

Duplicate an existing agent into a new agent named "Copy of <name>", carrying over its configuration. Use the include_* flags in the (optional) body to control what is copied; all default on except me…

Get an agent by ID.

Update an agent's display name or delivery settings.

Delete an agent and cascade-clean its schedules, case triggers, builder runs, and handover targets. Any active jobs are interrupted and their sandboxes paused.

Move an agent (and its connected workspace) to a different team. Pass dry_run=true to preview the closure without applying changes.

Get a single automation with its agent and queue counts, and the tab arrangement its detail view navigates by.

Update an automation, e.g. rename it. Only the fields present in the body are changed.

Get the automation detail view's tab arrangement, plus metadata for the Pulse dashboards pinned into it. Pinned dashboards are filtered to the ones the calling identity may see.

Soft-delete an automation. Its member agents and queues stop dispatching and disappear from listings, but their underlying rows and run history are preserved (not erased) so the automation can be rest…

Get what the automation is set up to do right now: its member agents with the builds that are live, its queues' routing, and the triggers and schedules firing for it. The revision-less counterpart of …

Get the automation's flow graph as it stands right now: the agents and queues it currently wires together, plus the producer, consumer, and handover edges between them. The revision-less counterpart o…

List integrations attached to an agent revision.

Attach one or more integrations to an agent revision. To pin specific connections after attachment, use pinRevisionIntegrationConnection. IMPORTANT for the case-queue-producer and case-queue-consumer …

Remove an integration from an agent revision. Removes the slot for everyone on the revision, including all per-user connection pins. Requires edit permission on the agent.

List the connections you have pinned to this build's integration slot. Multi-pin is supported: you can pin multiple connections to the same slot.

Pin one of your connections (from GET /v2/teams/:team_id/connections) to this build's integration slot. Multi-pin is supported: a single user can pin multiple connections to the same slot.

Unpin one of your connections from this build's integration slot. The connection itself is not deleted; only the binding to this slot is removed.

Check that this build's case-queue integration slots are wired up correctly. Returns, per case-queue-producer/consumer slot, how many queues are linked, plus whether any queue is available to bind (sc…

List the queues linked to this build's case-queue integration slot. Only meaningful for case-queue-producer and case-queue-consumer integrations.

Replace the set of queues linked to this build's case-queue integration slot. Send the full desired queue list — any queues not in the list will be unlinked. Requires edit permission on the agent. Aft…

List an Agent's suggestions. status=pending is the inbox; status=history is consumed/dismissed/auto-cleared. Reads lazily auto-clear stale pending items.

Fetch a single suggestion. Poll this after a 202 from consume: an AOP apply in flight reports payload.apply.state (running/failed); once consumed, applied_revision_id carries the draft revision the ch…

Apply a suggestion: stage its change into the Agent's draft revision, then auto-clear any pending suggestions it makes moot.

Dismiss a pending suggestion.

List all system skills (skills available to all teams).

Delete a skill for the current team.

Download a custom skill as a ZIP archive. Only custom (team-owned) skills can be downloaded.

List all files in a skill.

Get the content of a file in a skill.

Update the content of a file in a skill, overwriting the active revision in place — the previous content is not recoverable. Prefer the non-destructive flow when you can: createSkillRevision to open a…

List the agents in the current team whose live build references the given skill. Used to warn users that editing a skill will affect every agent that uses it.

List a skill's version history. Each revision is a snapshot of the skill's files; at most one is active (live) at a time, plus at most one open draft.

Open a draft revision of a skill, copying its files from the active revision (or from `source_revision_id`). Edit the draft with updateSkillRevisionFile, then activate it with promoteSkillRevision — t…

Make a skill revision the active (live) one. The previously active revision becomes historic and can be re-activated later. Idempotent: promoting the already-active revision succeeds rather than error…

List the files in a skill revision, one page at a time. When `has_more` is true, pass `next_cursor` back as `cursor` to fetch the next page.

Get the content of a text file in a skill revision.

Write a text file into a skill revision. Writing into a draft leaves the active revision untouched until the draft is promoted; writing into the active revision changes what the skill runs immediately…

Rename a skill revision or change its description. Works for drafts, the active revision, and historic revisions.

Delete a draft or historic skill revision and its files. The active revision can't be deleted — activate another revision first.

Get the profile of the authenticated user (the owner of the API key).

Get a legacy v1 Clarity process with process metadata, generated analysis, automation guidance, generation progress, and captures. Use this for rows from listClarityProcesses where version=1; v2 rows …

Update a Clarity process name, guidance, visibility, or completion status. Team Builders can edit names and guidance, only the creator or a team manager can change visibility, and completion requires …

List users with accepted access to a clarity process

Remove accepted access to a clarity process

Delete a Clarity process. The creator or a team admin can delete it unless capture analysis is still in progress.

Duplicate a Clarity process with its analysis, captures, message history, and, for v2 processes, its live current map and automation proposal. Requires a team manager role.

Create a signed URL for uploading a video file directly to GCS

Complete a video capture after uploading to GCS via signed URL

Create a signed URL for uploading a PDF, TXT, Markdown, BPMN, XLSX, or CSV document directly to GCS

Complete a document capture after uploading to GCS via signed URL

Create a signed URL for uploading a PNG, JPEG, or WebP image directly to GCS

Complete an image capture after uploading it to GCS via a signed URL

Invite the in-meeting notetaker bot (Recall.ai) to a live meeting; the recording lands as a 'meeting' capture on the process

Delete a capture from a clarity process

Create a new automation guidance message for a clarity process

Update the automation guidance message for a clarity process

Get the sharing status for a clarity process

Enable or disable sharing for a clarity process

Get the active interview invite link for a process.

Delete the active interview invite link for a process.

Get information about a clarity interview invite link (public).

Accept a clarity interview invite link and gain process access.

Rename a process landscape node or update its owner label (team manager or above for team processes; organization admin for areas)

Accept a proposed area folder into the active process landscape, so it stops being a proposal and becomes part of the real structure (organization admin+). Only area folders can be accepted; a propose…

Reject a proposed process landscape node while it is still a proposal, removing it and any proposed descendants. Real processes nested underneath survive and move back to Unsorted. Only proposals can …

Soft-delete a tree node and its descendants. Organization admins may delete any subtree; team managers may delete a childless process node owned by their team. The targeted node's linked clarity proce…

Move a process landscape node (team manager or above for team processes; organization admin for areas)

Reorder a sibling group of the organization's process landscape area folders left-to-right — the top-level areas by default, or the folder children of parentId (organization admin+). This changes disp…

Set the owning team of a process in the process landscape (organization admin+). On a proposed process this accepts the proposal and creates the real process for that team; on an existing process it m…

File an existing Clarity process into an area of the process landscape (team manager or organization admin+). Use this for a process that already exists but sits in Unsorted; use proposeClarityLandsca…

Create a manual process in the organization's Process Landscape, either as an unassigned proposal or atomically assigned to an eligible team.

Add one or more people to multiple Process Landscape nodes in a bounded batch. Email entries can create invitations; each node-person outcome reports success, conflict, or delivery failure.

List the people involved in the process behind one process landscape node. To read the people across the whole landscape in one request, use getClarityHierarchyPeople instead.

Add a person involved in the process behind a process landscape node. Name only records a placeholder; supplying an email also gives that person access to the process and emails them an invitation, so…

Change the role a person plays in the process behind a process landscape node (for example "Approver"). Send role: null to clear it.

Remove a person from the process behind a process landscape node, and revoke the process access they were granted when they were added.

Accept a pending Process Landscape team-assignment suggestion and durably assign the suggested team (manager+).

Dismiss a pending Process Landscape team-assignment suggestion without changing the node's owner (manager+).

Accept a pending Process Landscape capture suggestion and create the durable capture request (manager+).

Assign an open Process Landscape capture request to a team member, or unassign it by sending userId: null (manager+).

Dismiss a pending Process Landscape capture suggestion without creating a capture request (manager+).

List Clarity interviews linked to a process folder

Delete an organization-scoped folder interview

Get the v2 read model for a clarity process: the process row (with operational fields like generation_error, generation_progress, generation_started_at, generation_last_activity_at, custom_prompt), it…

Get a single Clarity v2 capture including full transcript and video transcript. Use this when the process was loaded with captures=lite, or when only one capture's transcript is needed.

Re-run postprocessing agents on an existing v2 clarity snapshot. Targets either the current-process snapshot or the automation proposal snapshot, identified by id in the body. Flips the process status…

Return one representative screenshare frame for each current-process step. Explicit frame evidence wins. Otherwise, a timestamped screenshare transcript source selects the closest persisted frame at o…

Hand an automation proposal for a v2 clarity process off to the workflow-builder pipeline. Builds from `transformation_proposal_id` when supplied, otherwise from the process's live proposal. The propo…

List active extra-capture requests for a given automation proposal of a Clarity v2 process. The caller is expected to know the proposal id from the V2 read model and skip the call when no proposal exi…

Assign (or unassign, with `user_id: null`) a team member to fulfil an extra-capture request. Restricted to admins and managers.

Create or regenerate a process-scoped Clarity interview invite link. Only the process creator or team managers can create invite links; creating a new link invalidates any prior active link for the pr…

Create a signed upload URL for importing a Miro export into a Clarity v2 process. Supports SVG, XML, PNG, and JPEG exports. The caller must upload the file to the returned URL, then complete the impor…

Complete a Miro artifact import after uploading to the signed URL. The uploaded bytes are validated before the import becomes a usable Clarity capture.

List the current user's recent non-deleted artifact-chat conversations for a Clarity v2 process and snapshot kind.

Load the latest artifact-chat messages for one active conversation, returned oldest-first.

Soft-delete an open or running artifact-chat conversation for the current user.

Stop an in-flight artifact-chat turn. Flips the conversation back to `open` first so the interrupted run's late webhooks are dropped as stale, then best-effort interrupts the cc-server execution.

Move a v1 clarity process into v2. Rows with generated analysis are reset in place and regenerated; rows without analysis migrate in place when not generating.

List lightweight Clarity v2 process snapshots for one kind.

Fetch the full payload for a Clarity v2 process snapshot of either kind.

Save user edits as the live Clarity v2 snapshot for the selected kind.

Promote a draft or historic Clarity v2 snapshot to live for its kind.

Archive a Clarity v2 snapshot of either kind. If the live row is archived, the repository auto-promotes the latest historic row of the same kind.

Trigger a snapshot generation pipeline for a v2 clarity process, selected by kind. `current_process` runs the generateCurrentProcess pipeline (body fields are proposal-only and rejected); `transformat…

Stop an in-flight snapshot generation for the selected kind. Reads the sandbox id from the process row, kills the sandbox, flips the process back to `review`, and clears the sandbox marker so any late…

Invite a person to an organization you administer, optionally assigning them to a team in that organization. Requires an organization Admin, Executive, or Owner role. You cannot grant a role higher th…

List teams belonging to an organization you are a member of, including your membership and role in each.

Get org-wide headline insight KPIs (run totals, success rate, distinct active agents and users) aggregated across every team in the organization. Requires an organization Admin, Executive, or Owner ro…

Get org-level insights metrics (runs, assignments, schedules) broken down per team across the organization. Requires an organization Admin, Executive, or Owner role.

Get org-level run-volume buckets (scheduled vs on-demand) at day/week/month granularity across the organization. Requires an organization Admin, Executive, or Owner role.

Create a new team under an organization you administer. Requires an organization Admin, Executive, or Owner role.

Start an asynchronous organization pass over the organization's unfiled processes, placing them into the Process Landscape where possible (organization admin+). Results appear progressively; started i…

Fetch the organization's process tree, or the subtree under rootId

Fetch the organization's full process landscape with process summaries, team assignments, and page-level stats

List the people attached to every authorized linked process node in the organization's Process Landscape. Returns a flat list where each person carries `nodeId` and `processId`, plus their role, invit…

List the organization's Process Landscape captures. By default, only captures eligible to seed new process proposals are returned; excluded captures can be included for inspection.

Start a process-landscape generation run for the organization from its eligible Clarity captures (organization executives and owners)

Create an area folder in the process tree. An active area (the default) requires organization admin+; a "proposal" area may be added by any organization member.

List process-to-process links in the organization's Clarity landscape that are visible within the caller's team access scope. Use `node_id` to find links touching a specific process node.

Create a process-to-process link in the organization's Clarity landscape when the caller can manage both endpoint teams. If the same live source, target, and type already exists, the existing link is …

Update a process-to-process link in the organization's Clarity landscape when the caller can manage both endpoint teams.

Delete a process-to-process link from the organization's Clarity landscape when the caller can manage both endpoint teams.

Set or clear heatmap priorities in one batch (team managers for their processes; organization admin+ across the organization)

List Clarity interviews across an organization

Load a single organization Clarity interview with transcript

Invite the in-meeting notetaker bot (Recall.ai) to a live meeting; the recording lands as an organization Clarity interview

Manually mark an in-progress organization interview as complete without requiring final media uploads

Rename an organization landscape Clarity capture

Delete an organization-level Clarity interview

Create a signed URL for uploading a PDF, TXT, Markdown, or BPMN document as an organization-level Clarity capture

Complete an organization document capture after uploading to GCS; extracts text and stores it as a transcript so it feeds Process Landscape generation

List the organizations the current user belongs to, with their role (organization:member, organization:admin, organization:owner, or organization:executive) and member count in each. Use this to check…

Get a Clarity export run by ID

Get a queue by ID.

List a queue's aggregation definitions.

Create an immutable aggregation definition on a queue.

Evaluate an aggregation definition against the current data without persisting it.

Read an aggregation definition's cached result.

Force a fresh recompute of an aggregation definition.

Soft-delete an aggregation definition.

Get a queue's Case schema settings: whether it requires typed cases, and the schema it validates them against.

Declare a queue's first Case schema by hand, so a person can type a queue up front instead of waiting for its producing agent to declare the shape. Fails if the queue already has a schema — replace an…

Replace a queue's Case schema with a new version. Every declared field is frozen against automated change, so this is the only way one can be edited.

Put a queue on an existing Case schema, so both queues share one document and a later change moves them together. The queue must not already have a schema.

Turn a queue's schema guard on or off, and freeze or unfreeze the schema document. A guarded queue with no schema yet asks its producing agent to declare one; a frozen schema refuses every change unti…

Stop validating new cases on a queue. Typed cases already written keep their payload and their pinned schema version.

Update a queue.

Delete a queue. Interrupts all associated active runs first and returns the number of deleted cases plus the IDs of runs that were stopped.

Export a queue's cases, respecting the same status, severity, priority, label, date-range, json_data field, and free-text filters as the list view. `format: "json"` (default) returns a re-importable J…

Get a case by ID. Returns the case, its event history, and every case-approval batch ever created on the case (newest first).

Edit a case's title and/or its free-form data payload. Provide at least one field. Works on pending, in-progress, and settled cases. Other attributes (status, priority, labels) have their own dedicate…

List Runs (agent runs) that have claimed or received handover of a case, newest first. Capped at 50 ownership events.

Return the latest qualifying messages (assistant text + tool calls) for a Run on a case, newest last. Used to populate the live body of an active Run card in the case Activity timeline.

Delete a case. Interrupts any associated active runs first.

Re-process multiple cases on a chosen agent. Any active runs on the selected cases are interrupted first; the cases are then reset to pending and assigned to the chosen agent for the next dispatcher t…

Update the status of multiple cases to pending, completed, failed, or canceled. Interrupts any active runs and releases their case ownership, but never cancels their human-in-the-loop state — pending …

Set the priority of multiple cases. Priority only affects the order pending cases are picked up in: due postponed cases are handled first, then higher priority. It never interrupts runs or changes cas…

List the files attached to a case, oldest first. Includes attachments whose upload failed, so a missing source document is visible rather than silent.

Issue a signed URL for uploading a file to a case. The client must PUT the bytes to the returned URL with the returned Content-Type, then call the finalize endpoint so the attachment becomes visible o…

Confirm an uploaded case attachment against storage. Answers with the attachment in its settled state — `ready` when the bytes are present, `failed` (with a reason) when the upload never completed.

Mint a short-lived signed URL for one case attachment. `disposition=inline` serves the file for the in-app viewer; `attachment` forces a download.

Remove a file from a case. The row is soft-deleted; deletion of the stored object is attempted best-effort.

Assign one or more labels to a case. Creates the labels on the queue if they don't already exist.

List all labels assigned to a case.

List every label defined on a queue along with the count of cases each label is assigned to.

Remove the given labels from a case.

Create a label on a queue without assigning it to a case.

Delete a label from a queue. Cascade-deletes all assignments of this label on existing cases.

Update a label's key, value, or color. Renaming key/value affects every case assigned to this label.

List agents bound to a queue as producers (agents that push cases into the queue) or consumers (agents triggered by cases in the queue).

List a queue's active case-level evaluation rubrics — the Pass/Fail questions a whole case is judged against at settlement. Shows the queue's current version's set (auto-generated from the connected A…

Add one case-level evaluation rubric to a queue's current rubric set. Case-level rubrics judge the whole case (across every Run that touched it) as a Pass/Fail question at settlement. The rubric is ad…

Replace the entire case-level evaluation rubric set on a queue's current version (1 to 12 rubrics). Existing rubrics are removed and the supplied list becomes the new set. An empty list is refused — w…

Edit a single case-level evaluation rubric's title and/or description. The edit produces a NEW rubric (with a new id and slug) so previously judged cases stay attributed to the original criterion; the…

Remove a single case-level evaluation rubric. Cases settled after this are no longer judged against it; already-judged cases keep their original verdicts. Removing the queue's last remaining rubric is…

List cases in a queue. Supports status, date-range, free-text, and json_data field filters via query params. Set count_only=true to skip Case row selection and transformation. The normal response shap…

Search cases in a queue with rich filters (multi-status, date ranges, label-based filters, and field-value filters over a typed queue's json_data). Use this when the simple query-string filters on GET…

Create one or more cases in a queue. Provide either a single `case` object or a `cases` array (1-100); providing both returns 400. Each case accepts a title (max 500 chars), optional free-form `data`,…

Get information about an agent run. Can be polled to check status.

Post a message to an agent run. This will persist the message and resume the agent execution if the run is in a resumable state (waiting, completed, or interrupted).

Get paginated messages for an agent run. Messages are returned in chronological order.

Respond to a human-in-the-loop request. Use 'approved' (true/false) for approval-type requests, or 'answers' ({question: answer}) for question-type requests. Only works when the run is in 'waiting' st…

Stop an agent run. No-op if the run is not currently running.

List teams the authenticated caller can act on. Team-scoped API keys see only the key's team; managed Ask Duvo keys stay within their origin boundary; human user-scoped API keys and OAuth callers see …

Rename an agent folder or move it to a new parent.

Delete an agent folder. If the folder contains assignments or subfolders, pass `force=true` to delete it and move the contained assignments to the root level.

Get one of your connections by ID.

Get the header keys configured for a connection. Sensitive values (api keys, tokens, passwords) are returned as empty strings — the response only reveals which credential fields are set, never their v…

Update an existing connection. For sensitive header values, sending an empty string keeps the existing value; send a new value to overwrite. Toggling `shared` moves the connection between personal and…

Delete a connection (disconnects the user's connection and removes any triggers bound to it).

Delete a custom integration type (team-level catalog entry) and cascade-remove related connections. Requires manager-or-above role.

Get an env-var secret by id. Returns metadata and env var keys; secret values are never exposed.

Update an env-var secret. Send `values` to replace all entries, or any of `rename_keys`, `remove_keys`, `add_values` for a non-destructive patch. Editing a team-shared secret or toggling sharing requi…

Soft-delete an env-var secret. Deleting a team-shared secret requires lead builder role.

List env-var secrets attached to a specific revision (build) of an assignment. Returns metadata and env-var keys only — secret values are never exposed.

Attach an env-var secret to a revision so its keys are injected into Runs spawned from that revision. Personal secrets can only be attached by their owner; team-shared secrets require builder permissi…

Detach an env-var secret from a revision. Personal secrets can only be detached by their owner; team-shared secrets require builder permissions.

List logins attached to a specific revision (build) of an assignment. Returns metadata only — passwords and OTP secrets are never exposed.

Attach a login to a revision so the agent can use it during Runs spawned from that revision. Personal logins can only be attached by their owner; team-shared logins require builder permissions.

Detach a login from a revision. Personal logins can only be detached by their owner; team-shared logins require builder permissions.

Get a single notification by id for the authenticated user. Requires the Notification Center feature; returns 404 when it is not enabled for the team.

Mark a notification as read for the authenticated user. Idempotent — calling it again on an already-read notification still returns success. Requires the Notification Center feature; returns 404 when …

Dismiss an important notification for the authenticated user. A row pinned to their Important section is unpinned and the card stays, because the connection is still broken; a row that is not pinned f…

List process tags available in an organization.

Create process tags for an organization.

Update process tags for an organization.

Delete process tags from an organization.

List process tags on a process.

Assign process tags to a process.

Remove process tags from a process.

List process tags available for a process.

List agents for your team.

Create a new agent. Optionally include a build configuration to create the first build in the same request.

List the team's automations, each with its live agent and queue counts. An automation is the workspace container an agent or queue belongs to on a team that has moved to Automations — its id is what `…

Create a new automation. Its first agent is created alongside it so the caller lands on something editable. On a team on revision semantics the automation holds a single draft revision and no live rev…

List all agent folders for the authenticated team.

Create a new agent folder.

Move one or more agents (assignments) into a folder, or to the root level.

List queues for your team.

Create a new queue.

Get case status counts for many Queues in ONE call. Use this after listQueues whenever you need per-Queue counts — cases waiting on a human, needing review, pending, failed — instead of calling listCa…

List runs for the current team. Supports filtering by agent, user, queue, status, etc. Messages, evaluation data, and queue metadata are included where available. Set count_only=true to skip Run row s…

Start a new agent run. Returns immediately with run info - does not wait for completion.

List all skills for the current team, including system skills.

Create or update a skill from a JSON body. The server constructs SKILL.md from the provided fields and stores it. If a skill with the same name already exists in the team, it is updated.

List Clarity processes for the current team, most recently updated first. Returns lightweight metadata (capture counts, contributors, status) suitable for building a picker; the per-process read model…

Cross-process portfolio digest for every completed Clarity process on the team: per-process summary, SWOT, projected impact, and a step skeleton (role, system, and flow edges) — without step prose or …

Create a new Clarity v2 process for the current team (Builder+). Optional `name` defaults server-side when omitted. Response uses camelCase `createdAt` to match existing FE clients.

List files for the current team.

Generate a signed URL for uploading a file directly to GCS.

Rename a file in team storage.

Delete a file from team storage.

Generate a signed download URL for a file.

Get the content of a text file.

Update the content of a text file.

List the team's integration catalog: built-in integration types plus any custom connection types defined for the team. OAuth authorization flows are browser-based and cannot be performed via this API;…

Create a custom integration type (team-level catalog entry) that users can then connect as user-provided MCP connections. Requires manager-or-above role.

List the authenticated user's connections (connected integration instances) for the current team. Includes team-shared instances visible to the caller when the org-level Connections sharing setting is…

Create a new user-provided connection (custom MCP server) for the current team. OAuth-based integrations (native) require an interactive browser flow — start them with the dedicated OAuth endpoints (`…

Probe an MCP server URL and list the tools it exposes. Useful as a dry-run before creating a connection — verifies the URL is reachable, that authentication headers (if any) are correct, and surfaces …

List env-var secrets visible to the caller — team-shared (user_id IS NULL) plus the caller's own personal entries. Returns metadata and env-var keys only; secret values are never exposed.

Create an env-var secret. Personal by default; pass `shared: true` to create a team-shared secret (requires lead builder role).

Invite one person to a team. Pass `processId` to invite them to a specific Clarity process instead of the whole team (that requires the `team:clarity-member` role). Creating the invitation does NOT em…

Revoke an invitation so its link and email can no longer be used. Accepts either a team invitation (requires Superadmin or above on the invitation's team) or a Clarity process invitation (requires the…

Email an invitation to its recipient. Use this to deliver an invitation created by createTeamInvite (which never sends mail on its own), or to resend one the recipient never received. The accept link …

Invite several people to a team in one call, emailing each invitation immediately. Returns per-batch counts: `succeeded` were invited, `skipped` were already on the team, already had a pending invitat…

Change the role on a pending team invitation. Only pending invitations can be updated — one already accepted or declined is rejected. Requires the Manager role or above on the invitation's own team.

Get the team's shareable invite link — the one URL anyone can use to join the team, as opposed to a per-person invitation. Returns `hasLink: false` when no link has been created. Requires the Manager …

Create or regenerate the team's shareable invite link — the one URL anyone can use to join the team. Regenerating invalidates the previous link, so anyone still holding the old URL can no longer join.…

Delete the team's shareable invite link so the URL stops working. Per-person invitations are unaffected. Requires the Manager role or above.

List notifications for the authenticated user's current team, most recent first. Filter with type, unread, severity or minSeverity (mutually exclusive), important, agentRunId, or processId; paginate w…

List the notification feed for the authenticated user's current team, most recent activity first. Each item is either an individual notification or a notification batch (a per-agent group of job_issue…

Get a single notification batch by id for the authenticated user, with per-type live-member counts, unread count, and worst severity. Serves cold deep links and sidebar retention for batches the calle…

Mark every unread live member of a notification batch as read for the authenticated user. Pass `types` to narrow the mark-read to those member types, and `severity` (exact) or `minSeverity` (threshold…

Get the unread notification count for the authenticated user's current team. Each notification batch with unread members counts as 1, regardless of its member count. Requires the Notification Center f…

Per-type notification counts for the authenticated user's current team. Narrow with `unread`, `important`, and with either `severity` (counts only that exact severity) or `minSeverity` (counts that ur…

Mark all notifications as read for the authenticated user's current team. Returns the count of notifications that were updated. Requires the Notification Center feature; returns 404 when it is not ena…

Soft-delete all read notifications for the authenticated user's current team. Returns the count of notifications that were deleted. Destructive — only call on explicit user request. Requires the Notif…

Soft-delete all notifications for the authenticated user's current team, read or unread. Returns the count of notifications that were deleted. Destructive — only call on explicit user request, never b…

List members of a team. The authenticated session or API key must be scoped to the requested team.

Update an existing team member's role. Requires the Manager role or above; only an Owner may grant or remove the Owner role, and the last remaining Owner cannot be demoted. A member whose Owner role i…

Remove a member from a team. Removing another member requires the Superadmin role or above; any member may remove themselves (leaving the team). The last remaining Owner cannot be removed, and a membe…

List a team's pending invitations — everyone invited who has not yet accepted or declined. Pass `processId` to list the pending invitations for a single Clarity process instead.

List browser-login credentials visible to the caller for the current team — team-shared (user_id IS NULL) plus the caller's own personal logins. Optionally filter by `domain`. Passwords and OTP secret…

Create a login. At least one of `password` or `otp_secret` must be provided. Personal by default; pass `shared: true` to create a team-shared login (requires lead builder role).

Get a login by id. Returns the encrypted password/otp_secret blobs — only the owner or team members can access it.

Update a login by id. At least one of password or otp_secret must remain set after the update. Editing a team-shared login or toggling sharing requires lead builder role.

Delete a login by id. Deleting a team-shared login requires lead builder role.

List active (queued or running) Clarity export jobs for the current user

Start a Clarity → SAP Signavio export job

List the team's process folders with process and suggestion counts

Create a process folder

Rename a process folder. Renaming a landscape-linked folder permanently stops landscape name-sync.

Delete a process folder. Contained processes fall back to Unfiled.

Reorder the team's process folders to match the given id order. The payload must name every folder exactly once.

Create one linked folder per landscape group node containing this team's processes. Idempotent: groups that already have a linked folder are skipped.

Move processes into a folder (or back to Unfiled)

File every unfiled process the viewer can see into its suggested folder

List team-level Clarity interviews

Delete a team-level Clarity interview

Create a signed URL for uploading a PDF, TXT, Markdown, or BPMN document as a team-level Clarity capture

Complete a team document capture after uploading to GCS; extracts text and stores it as a transcript so it feeds Process Landscape generation

Get clarity team settings for financial calculations

Update clarity team settings for financial calculations

Get portfolio intelligence for the current team

Generate portfolio intelligence from all completed clarity processes. Returns 202 Accepted immediately and processes in background.

Move a Pulse dashboard from the team in the URL to another team, keeping only its latest revision (chat history and older revisions are deleted). The caller must be a Manager or above on both teams. P…

Draft, rewrite, or critique a Duvo Agent AOP. Use when the user wants to improve an existing AOP or write a new one from a brief. Returns the AOP as a single complete markdown document in the canonica…

Reference material for the aop-writer skill (SKILL.md says when to read it).

Reference material for the aop-writer skill (SKILL.md says when to read it).

Reference material for the aop-writer skill (SKILL.md says when to read it).

Reference material for the aop-writer skill (SKILL.md says when to read it).

Diagnose and health-check the Connections and credentials a Duvo Agent relies on. Use when the user asks whether a Connection is set up or available, why an Agent is blocked on authentication, what a …

Run the guided, end-to-end loop that makes one Duvo Agent better. Use when the user wants to "improve this Agent", "make my Agent better", "help me tune this Agent", "this Agent isn't good enough", "f…

Run the guided, end-to-end loop that makes one Duvo Queue — and the producer→consumer workflow around it — better. Use when the user wants to "improve this Queue", "this Queue keeps backing up, fix it…

Investigate why a Duvo Run failed or produced the wrong outcome. Use when the user shares a failed Run, asks "why did this Run fail", or wants to fix a recurring failure on an Agent. Reads the Run's t…

Audit a Duvo Agent — or a multi-Agent workflow connected by a Queue — across many Runs to find systemic inefficiencies and quality issues, then recommend concrete AOP and architecture changes. Use whe…