by aioproductos
AIOProductOS spine over MCP — customers, revenue, feedback, work, analytics on one typed record.
AIOProductOS spine over MCP — customers, revenue, feedback, work, analytics on one typed record.
Captured live from the server via tools/list.
How to operate as a product manager on AIOProductOS — ground in the brain, keep work tied to the spine (insight→feature→task→outcome), prioritise on evidence (affected accounts + MRR + reach). Read-only; returns the operating guide as plain text. Call it first, before planning or prioritising, to load the house rules the other tools assume.
Parameters
No parameters.
{
"type": "object",
"properties": {}
}Show the connected AIOProductOS identity (org, member) AND the org's products (id, name, is_primary). Read-only; returns the identity plus the product list. For a multi-product org, call this first to get the product ids, then pass one as `product_id` to any product-scoped tool; omit product_id to use the primary.
Parameters
No parameters.
{
"type": "object",
"properties": {}
}List the org's PM lists, statuses, members, and features as id+name pairs. Read-only; returns arrays for resolution only (list_features carries the richer catalogue). Call it to turn a name into an id before create_task / update_task — never guess an id.
Parameters
No parameters.
{
"type": "object",
"properties": {}
}A grounded, read-only snapshot of the org's product so YOU can reason about it: revenue + top paying accounts, web + product analytics, features, recent verbatim customer signals, and open work. Start here to ground, then go deeper with the dedicated list_* reads and the analytics tools. Optional product_id; omit for the primary product.
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
}
}
}The Weekly Product Signal Memo — the last 7 days of customer signal clustered into themes (insights grouped by feature, ranked by the revenue behind them) with verbatim quotes, week-over-week deltas (new / repeated / stronger / weaker), concluded experiments, and shipped releases. Deterministic — every count is off real rows, no fabricated quotes. Optional `week` (ISO 'YYYY-Www') for a past week; `generate=1` rebuilds + persists the current week now. Read-only apart from that rebuild; returns the persisted memo, empty when the requested week has none. Open a weekly review with it, then drill into a theme with list_insights.
| week | string | optional | ISO week to fetch, format 'YYYY-Www' e.g. '2026-W27' (optional; the latest persisted week when omitted). |
| generate | string | optional | Pass '1' to rebuild and persist the current week's memo now instead of reading the stored one (optional). |
{
"type": "object",
"properties": {
"week": {
"type": "string",
"description": "ISO week to fetch, format 'YYYY-Www' e.g. '2026-W27' (optional; the latest persisted week when omitted)."
},
"generate": {
"type": "string",
"description": "Pass '1' to rebuild and persist the current week's memo now instead of reading the stored one (optional)."
}
}
}Planned vs shipped features over a window: a drift score (0-100, 100 = perfect alignment), counts (planned / shipped / on-time / slipped / unplanned / orphaned), median slip days, and the top slipped + unplanned ships. Deterministic, no LLM cost. window = week | month | quarter (default quarter); optional product_id. Read-only; returns the drift report, zeroed when nothing was planned or shipped in the window. Use it in planning reviews to check delivery against the roadmap, then open the slipped features with list_features.
| window | string | optional | Lookback window to compare planned vs shipped over (optional; default quarter). |
| product_id | string | optional | Product id, from whoami (optional; spans all the org's products when omitted). |
{
"type": "object",
"properties": {
"window": {
"type": "string",
"enum": [
"week",
"month",
"quarter"
],
"description": "Lookback window to compare planned vs shipped over (optional; default quarter)."
},
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; spans all the org's products when omitted)."
}
},
"examples": [
{
"window": "quarter"
}
]
}Everything about ONE customer, resolved by id, email, domain, or company name: profile, subscription + MRR, how many users sit under the account, and their verbatim feedback. Read-only; returns the matched account, or an empty result when nothing matches the query. The money + people + voice join on one record — call it before answering anything about a specific account.
| query | string | required | The account to resolve: an account id, a user's email, a company domain (e.g. 'acme.com'), or a company name. |
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The account to resolve: an account id, a user's email, a company domain (e.g. 'acme.com'), or a company name."
}
},
"required": [
"query"
],
"examples": [
{
"query": "acme.com"
}
]
}NPS for the product — standard score AND revenue-weighted NPS (each respondent weighted by their account MRR), plus the detractor accounts ranked by what they're worth. Surfaces when your biggest customers are the unhappy ones even if the headline looks fine. Optional product_id and window_days (default 90). Read-only; returns an empty result when no survey responses fall in the window. Use it to quantify sentiment after get_product_brain, then dig into a detractor account with get_customer_360.
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
| window_days | number | optional | Lookback window in days (optional; default 90, i.e. the last quarter). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
},
"window_days": {
"type": "number",
"description": "Lookback window in days (optional; default 90, i.e. the last quarter)."
}
},
"examples": [
{
"window_days": 90
}
]
}Net Revenue Retention (revenue-weighted) next to logo retention (count-weighted), the expansion/contraction/churn split, and the accounts that lost the most MRR. The divergence is the point: '92% of logos but 78% of revenue' means a big account churned. Optional window_days (default 90). Read-only; returns an empty result when no subscription movements fall in the window. Use it to quantify revenue health, then follow the top-losing accounts into get_customer_360.
| window_days | number | optional | Lookback window in days (optional; default 90, i.e. the last quarter). |
{
"type": "object",
"properties": {
"window_days": {
"type": "number",
"description": "Lookback window in days (optional; default 90, i.e. the last quarter)."
}
},
"examples": [
{
"window_days": 90
}
]
}Build a conversion funnel from the product's own events: distinct users per step, step-to-step conversion, and drop-off. Read-only; needs product analytics events flowing, and returns empty counts when no events match. Pass `steps` as an ordered list of 2+ event names — call it with no steps first to get the menu of available event names rather than guessing. Optional product_id and window_days (default 30); pairs with analyze_paths to see where the drop-offs go.
| steps | array | optional | Ordered list of 2+ event names forming the funnel; omit to get the menu of available event names first. |
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
| window_days | number | optional | Lookback window in days (optional; default 30). |
{
"type": "object",
"properties": {
"steps": {
"type": "array",
"items": {
"type": "string"
},
"description": "Ordered list of 2+ event names forming the funnel; omit to get the menu of available event names first."
},
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
},
"window_days": {
"type": "number",
"description": "Lookback window in days (optional; default 30)."
}
},
"examples": [
{
"steps": [
"signup",
"activated",
"subscribed"
]
}
]
}Weekly cohort retention for the product: users grouped by first-seen week, with the share returning each week after. Read-only; needs product analytics events flowing, and returns empty cohorts when the product has none. Optional product_id and window_days (default 56 = 8 weekly cohorts).
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
| window_days | number | optional | Lookback window in days (optional; default 56 = 8 weekly cohorts). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
},
"window_days": {
"type": "number",
"description": "Lookback window in days (optional; default 56 = 8 weekly cohorts)."
}
},
"examples": [
{
"window_days": 56
}
]
}Trace what users do AFTER a start event — the journey flow (Sankey) from the product's own events. Read-only; returns the ranked next-step transitions, empty when no events match. Pass `start` to anchor on an event, or omit for the most common start (call analyze_funnel with no steps to see the available event names). Optional product_id and window_days (default 30).
| start | string | optional | Event name to anchor the flow on (optional; the most common start event when omitted — analyze_funnel with no steps lists the event names). |
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
| window_days | number | optional | Lookback window in days (optional; default 30). |
{
"type": "object",
"properties": {
"start": {
"type": "string",
"description": "Event name to anchor the flow on (optional; the most common start event when omitted — analyze_funnel with no steps lists the event names)."
},
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
},
"window_days": {
"type": "number",
"description": "Lookback window in days (optional; default 30)."
}
},
"examples": [
{
"start": "signup"
}
]
}List the org's board tasks and return the matches with their status, priority, assignees, and any linked feature/insight/sprint. Optionally narrow by status_id or list_id — resolve either via pm_meta. Read-only; returns an empty list when nothing matches. Use it to find a task id before get_task, update_task, or comment_on_task.
| status_id | string | optional | Only tasks in this status; resolve the id via pm_meta (optional). |
| list_id | string | optional | Only tasks on this list; resolve the id via pm_meta (optional). |
{
"type": "object",
"properties": {
"status_id": {
"type": "string",
"description": "Only tasks in this status; resolve the id via pm_meta (optional)."
},
"list_id": {
"type": "string",
"description": "Only tasks on this list; resolve the id via pm_meta (optional)."
}
}
}Get one task by id and return it with its full comments and assignees. Read-only. Resolve the id first with list_tasks — never guess it; pair with update_task or comment_on_task to act on what you read.
| id | string | required | Task id, from list_tasks. |
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Task id, from list_tasks."
}
},
"required": [
"id"
],
"examples": [
{
"id": "task_8f3a"
}
]
}Create a task and return the created task. list_id defaults to the org's first list when omitted; feature_id / insight_id link it to the spine and sprint_id schedules it into a sprint. Resolve list/status/feature/insight/member ids via pm_meta and sprint_id via list_sprints — never guess them. Only title is required.
| title | string | required | Task title (the only required field). |
| description | string | optional | Task body / details (optional). |
| priority | string | optional | Priority level, urgent highest (optional). |
| list_id | string | optional | List to create the task on; resolve the id via pm_meta (optional; the org's first list when omitted). |
| status_id | string | optional | Initial status; resolve the id via pm_meta (optional). |
| feature_id | string | optional | Feature id to link on the spine, from pm_meta or list_features (optional). |
| insight_id | string | optional | Insight id to link on the spine, from list_insights (optional). |
| sprint_id | string | optional | Schedule into a sprint (optional; resolve the id via list_sprints). |
| assignee_member_ids | array | optional | Member ids to assign, from pm_meta (optional). |
{
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "Task title (the only required field)."
},
"description": {
"type": "string",
"description": "Task body / details (optional)."
},
"priority": {
"type": "string",
"enum": [
"urgent",
"high",
"normal",
"low"
],
"description": "Priority level, urgent highest (optional)."
},
"list_id": {
"type": "string",
"description": "List to create the task on; resolve the id via pm_meta (optional; the org's first list when omitted)."
},
"status_id": {
"type": "string",
"description": "Initial status; resolve the id via pm_meta (optional)."
},
"feature_id": {
"type": "string",
"description": "Feature id to link on the spine, from pm_meta or list_features (optional)."
},
"insight_id": {
"type": "string",
"description": "Insight id to link on the spine, from list_insights (optional)."
},
"sprint_id": {
"type": "string",
"description": "Schedule into a sprint (optional; resolve the id via list_sprints)."
},
"assignee_member_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Member ids to assign, from pm_meta (optional)."
}
},
"required": [
"title"
],
"examples": [
{
"title": "Fix SSO redirect loop",
"priority": "high",
"feature_id": "feat_sso"
}
]
}Agent-as-critic over a DRAFT artifact (a feature spec, experiment plan, or page): checks it against a baseline PM bar — clear problem/hypothesis, a measurable success metric, evidence cited, risks named, a rollout/experiment plan — and returns structured findings (section, severity, a CONCRETE suggested fix, and a verbatim evidence quote) plus a 0-100 score. A write: each call re-runs the review and persists it as a new version (see list_artifact_versions). Resolve target_id first — via pm_meta or list_features for a feature, list_experiments for an experiment, list_pages for a page. One small LLM call; use it before sending a draft for sign-off.
| target_id | string | required | Id of the feature/experiment/page to review — from pm_meta, list_features, list_experiments, or list_pages. |
| target_type | string | required | What kind of artifact target_id is: a feature (spec), an experiment (plan), or a page (doc/PRD). |
| rubric_id | string | optional | Score against a specific rubric; omit to use the org's default rubric (or the built-in baseline). |
{
"type": "object",
"properties": {
"target_id": {
"type": "string",
"description": "Id of the feature/experiment/page to review — from pm_meta, list_features, list_experiments, or list_pages."
},
"target_type": {
"type": "string",
"enum": [
"feature",
"experiment",
"page"
],
"description": "What kind of artifact target_id is: a feature (spec), an experiment (plan), or a page (doc/PRD)."
},
"rubric_id": {
"type": "string",
"description": "Score against a specific rubric; omit to use the org's default rubric (or the built-in baseline)."
}
},
"required": [
"target_id",
"target_type"
],
"examples": [
{
"target_type": "feature",
"target_id": "feat_8f3a"
}
]
}Version history of an artifact's AI reviews (F5): every review run is a version with its score, model, cost, who/what generated it, and whether it's the current one. Read-only; returns the version list, empty when the artifact has never been reviewed. Use it to see how a feature/experiment/page's review changed over time and to pick the version_id to pass to revert_to_version. Takes the same target_id/target_type you'd pass to review_artifact.
| target_id | string | required | Id of the reviewed feature/experiment/page — the same id passed to review_artifact. |
| target_type | string | required | What kind of artifact target_id is: a feature (spec), an experiment (plan), or a page (doc/PRD). |
{
"type": "object",
"properties": {
"target_id": {
"type": "string",
"description": "Id of the reviewed feature/experiment/page — the same id passed to review_artifact."
},
"target_type": {
"type": "string",
"enum": [
"feature",
"experiment",
"page"
],
"description": "What kind of artifact target_id is: a feature (spec), an experiment (plan), or a page (doc/PRD)."
}
},
"required": [
"target_id",
"target_type"
],
"examples": [
{
"target_id": "feat_8f3a",
"target_type": "feature"
}
]
}Restore an earlier artifact version (F5) to current and return the now-current version: the existing current version is flipped to 'reverted' (kept for the learning signal) and the chosen version becomes current again. A write — not idempotent, since re-running reverts again. version_id is the version you want to RESTORE; get it from list_artifact_versions and never guess it. Optional reason is recorded.
| version_id | string | required | Id of the version to restore (make current), from list_artifact_versions. |
| reason | string | optional | Why you're reverting (optional, recorded). |
{
"type": "object",
"properties": {
"version_id": {
"type": "string",
"description": "Id of the version to restore (make current), from list_artifact_versions."
},
"reason": {
"type": "string",
"description": "Why you're reverting (optional, recorded)."
}
},
"required": [
"version_id"
],
"examples": [
{
"version_id": "ver_8f3a",
"reason": "new review missed the metric finding"
}
]
}Update one or more of a task's fields and return the updated task; fields you omit are left unchanged (idempotent — re-sending the same values is a no-op). Pass sprint_id: null to remove the task from its sprint. Resolve ids first — the task via get_task/list_tasks, and status/feature/insight/sprint/member ids via pm_meta and the list_* reads — never guess them. Only id is required.
| id | string | required | Task id, from list_tasks or get_task. |
| title | string | optional | New title (optional; omitted fields stay unchanged). |
| description | string | optional | New body / details (optional). |
| priority | string | optional | New priority level, urgent highest (optional). |
| status_id | string | optional | New status; resolve the id via pm_meta (optional). |
| feature_id | string | optional | Feature id to link on the spine, from pm_meta or list_features (optional). |
| insight_id | string | optional | Insight id to link on the spine, from list_insights (optional). |
| sprint_id | string | optional | Move into a sprint, or null to remove (optional; resolve via list_sprints). |
| assignee_member_ids | array | optional | Member ids to assign, from pm_meta (optional). |
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Task id, from list_tasks or get_task."
},
"title": {
"type": "string",
"description": "New title (optional; omitted fields stay unchanged)."
},
"description": {
"type": "string",
"description": "New body / details (optional)."
},
"priority": {
"type": "string",
"enum": [
"urgent",
"high",
"normal",
"low"
],
"description": "New priority level, urgent highest (optional)."
},
"status_id": {
"type": "string",
"description": "New status; resolve the id via pm_meta (optional)."
},
"feature_id": {
"type": "string",
"description": "Feature id to link on the spine, from pm_meta or list_features (optional)."
},
"insight_id": {
"type": "string",
"description": "Insight id to link on the spine, from list_insights (optional)."
},
"sprint_id": {
"type": "string",
"description": "Move into a sprint, or null to remove (optional; resolve via list_sprints)."
},
"assignee_member_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Member ids to assign, from pm_meta (optional)."
}
},
"required": [
"id"
],
"examples": [
{
"id": "task_8f3a",
"status_id": "status_in_progress"
},
{
"id": "task_8f3a",
"sprint_id": "sprint_2026_w27"
}
]
}Add a comment to a task, authored as the connected member, and return the created comment. Use to record progress, a decision, or a handoff — the comment is visible to the whole org, so keep it work-relevant. Resolve the task id first with get_task or list_tasks; both id and body are required.
| id | string | required | Task id, from list_tasks or get_task. |
| body | string | required | Comment text; posted as the connected member and visible to the whole org. |
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Task id, from list_tasks or get_task."
},
"body": {
"type": "string",
"description": "Comment text; posted as the connected member and visible to the whole org."
}
},
"required": [
"id",
"body"
],
"examples": [
{
"id": "task_8f3a",
"body": "Shipped behind a flag — verifying in production."
}
]
}Write a piece of customer feedback to the spine (the agent's own hand, not just reading) and return the created insight. Fires the same insight.created webhook a manual capture does — a real side-effect, so only capture genuine signal. Resolve account_id via get_customer_360 and feature_id via list_features and tie them when known; kind='opportunity' marks a prioritisable ask. Only body is required.
| body | string | required | The verbatim feedback / insight text (the only required field). |
| title | string | optional | Short display title (optional). |
| kind | string | optional | 'insight' = raw signal; 'opportunity' = a prioritisable ask (optional). |
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
| feature_id | string | optional | Feature id to link on the spine, from list_features or pm_meta (optional). |
| account_id | string | optional | Account id it's about, from get_customer_360 (optional). |
{
"type": "object",
"properties": {
"body": {
"type": "string",
"description": "The verbatim feedback / insight text (the only required field)."
},
"title": {
"type": "string",
"description": "Short display title (optional)."
},
"kind": {
"type": "string",
"enum": [
"insight",
"opportunity"
],
"description": "'insight' = raw signal; 'opportunity' = a prioritisable ask (optional)."
},
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
},
"feature_id": {
"type": "string",
"description": "Feature id to link on the spine, from list_features or pm_meta (optional)."
},
"account_id": {
"type": "string",
"description": "Account id it's about, from get_customer_360 (optional)."
}
},
"required": [
"body"
],
"examples": [
{
"body": "Two enterprise accounts asked for SAML this week.",
"kind": "opportunity",
"account_id": "acct_acme",
"feature_id": "feat_sso"
}
]
}List support-chat conversations in the inbox (open + snoozed by default; pass status='all' to include closed). Read-only; returns the matching conversations, empty when the inbox is clear. Optional product_id to scope to one product; open a full thread with get_conversation.
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
| status | string | optional | Pass 'all' to include closed (optional). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
},
"status": {
"type": "string",
"enum": [
"all"
],
"description": "Pass 'all' to include closed (optional)."
}
}
}Read one support conversation: the visitor plus the full message thread, oldest first. Read-only. Resolve the conversation_id first with list_conversations — never guess it.
| conversation_id | string | required | Conversation id, from list_conversations. |
{
"type": "object",
"properties": {
"conversation_id": {
"type": "string",
"description": "Conversation id, from list_conversations."
}
},
"required": [
"conversation_id"
],
"examples": [
{
"conversation_id": "conv_42"
}
]
}Search the captured insight backlog (voice of customer) — the read twin of capture_insight. Read-only; returns the matching insights newest first, empty when nothing matches. Filters: status, kind (insight|opportunity), feature_id, account_id, product_id, and free-text q over title+body; limit default 50, max 200. Use it to survey the evidence behind a feature or account before prioritising — resolve feature_id via list_features and account_id via get_customer_360.
| q | string | optional | Free-text search over title + body (optional). |
| status | string | optional | Only insights in this workflow status (optional). |
| kind | string | optional | 'insight' = raw signal; 'opportunity' = a prioritisable ask (optional). |
| feature_id | string | optional | Only insights linked to this feature; resolve the id via list_features or pm_meta (optional). |
| account_id | string | optional | Only insights about this account; resolve the id via get_customer_360 (optional). |
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
| limit | number | optional | Max rows to return (optional; default 50, max 200). |
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Free-text search over title + body (optional)."
},
"status": {
"type": "string",
"description": "Only insights in this workflow status (optional)."
},
"kind": {
"type": "string",
"enum": [
"insight",
"opportunity"
],
"description": "'insight' = raw signal; 'opportunity' = a prioritisable ask (optional)."
},
"feature_id": {
"type": "string",
"description": "Only insights linked to this feature; resolve the id via list_features or pm_meta (optional)."
},
"account_id": {
"type": "string",
"description": "Only insights about this account; resolve the id via get_customer_360 (optional)."
},
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
},
"limit": {
"type": "number",
"description": "Max rows to return (optional; default 50, max 200)."
}
},
"examples": [
{
"q": "SSO",
"kind": "opportunity"
}
]
}The product's feature catalogue with description, status, and when each was last touched — richer than pm_meta (which is just id+name for resolution). Read-only; returns the matching features, empty when none. Optional product_id and free-text q over name+key; use a feature id from here to link a task or insight on the spine.
| q | string | optional | Free-text search over feature name + key (optional). |
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Free-text search over feature name + key (optional)."
},
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
}
}
}OKRs — objectives with their key results and live progress (0..1 between start and target), so you can prioritise toward what the team is actually trying to move. Read-only; returns the objectives, empty when none are set. Optional product_id.
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
}
}
}Experiments — hypothesis, metric, target, state, verdict, and the decision that came out. Read-only; returns the matching experiments, empty when none. See what's being tested and what it concluded. Optional product_id and state filters.
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
| state | string | optional | Only experiments in this state, e.g. 'running' (optional). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
},
"state": {
"type": "string",
"description": "Only experiments in this state, e.g. 'running' (optional)."
}
},
"examples": [
{
"state": "running"
}
]
}The release log — version, changelog, and ship date, newest first. Read-only; answers 'what did we ship recently?' and returns an empty list when nothing has shipped. Optional product_id.
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
}
}
}List the in-product docs / PRDs (Pages) on the spine — titles + ids only, no content. Read-only; returns the page list, empty when none exist. Call get_page with an id to read one. Optional product_id.
| product_id | string | optional | Product id to scope to, from whoami (optional; spans all products when omitted). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id to scope to, from whoami (optional; spans all products when omitted)."
}
}
}Read one Page (doc / PRD) by id and return its full content. Read-only. Resolve the id first with list_pages — never guess it.
| id | string | required | Page id, from list_pages. |
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Page id, from list_pages."
}
},
"required": [
"id"
],
"examples": [
{
"id": "page_12"
}
]
}The auto-generated codebase brain map for one product: a plain-language summary, the module/node/edge counts, when the map was last generated, and the labels of the modules it found. Read-only; returns the latest generated map, empty when none has been generated for the product yet. Use it to ground 'where in the code does X live?' questions and to see how the codebase splits into modules before discussing architecture or scoping engineering work. Optional product_id, from whoami; omit for the org's primary product.
| product_id | string | optional | Product id, from whoami (optional; the org's primary product when omitted). |
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description": "Product id, from whoami (optional; the org's primary product when omitted)."
}
}
}Sprints — name, goal, state, and window, newest first. Read-only; returns the matching sprints, empty when none exist. See the delivery cadence (active + recent), and resolve a sprint_id here before scheduling a task via create_task / update_task. Optional state filter (e.g. 'active').
| state | string | optional | Filter by state, e.g. 'active' (optional). |
{
"type": "object",
"properties": {
"state": {
"type": "string",
"description": "Filter by state, e.g. 'active' (optional)."
}
},
"examples": [
{
"state": "active"
}
]
}List the team Comms channels the connected member belongs to (membership-scoped). Read-only; returns the member's channels, empty when they belong to none. Call read_channel with a channel_id to read one.
Parameters
No parameters.
{
"type": "object",
"properties": {}
}Read a Comms channel's recent messages, newest included (the connected member must be a channel member). Read-only; returns the messages, empty when the channel is silent. Resolve channel_id first with list_channels — never guess it. Optional limit.
| channel_id | string | required | Channel id, from list_channels. |
| limit | number | optional | Max messages to return (optional). |
{
"type": "object",
"properties": {
"channel_id": {
"type": "string",
"description": "Channel id, from list_channels."
},
"limit": {
"type": "number",
"description": "Max messages to return (optional)."
}
},
"required": [
"channel_id"
],
"examples": [
{
"channel_id": "chan_eng",
"limit": 50
}
]
}Upcoming confirmed bookings on the org's scheduling. Read-only; returns the bookings, empty when none are scheduled. Pass include='all' for full history.
| include | string | optional | Pass 'all' for history (optional). |
{
"type": "object",
"properties": {
"include": {
"type": "string",
"enum": [
"all"
],
"description": "Pass 'all' for history (optional)."
}
}
}Clusters of ≥2 end_users seen on the same device: 'anon_bridge' (high confidence — an anonymous visitor later identified) or 'device_shared' (low confidence — review only). Read-only; returns the candidate clusters, empty when none are found. Use it to find merge targets, then act with merge_end_users.
Parameters
No parameters.
{
"type": "object",
"properties": {}
}Merge source end-users into a target and return the merge result: all FK rows (events, insights, tasks, …) are re-pointed onto the target and the sources are tombstoned. A write; reversible for 30 days via unmerge_end_users. Get the candidate ids from get_device_candidates first — never guess which users to fold together. target_end_user_id and source_end_user_ids are required.
| target_end_user_id | string | required | UUID of the end-user to keep, from get_device_candidates. |
| source_end_user_ids | array | required | UUIDs of end-users to fold into the target, from get_device_candidates. |
| reason | string | optional | Why the merge (optional, recorded). |
{
"type": "object",
"properties": {
"target_end_user_id": {
"type": "string",
"description": "UUID of the end-user to keep, from get_device_candidates."
},
"source_end_user_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "UUIDs of end-users to fold into the target, from get_device_candidates."
},
"reason": {
"type": "string",
"description": "Why the merge (optional, recorded)."
}
},
"required": [
"target_end_user_id",
"source_end_user_ids"
],
"examples": [
{
"target_end_user_id": "eu_keep",
"source_end_user_ids": [
"eu_discard"
],
"reason": "device:anon_bridge"
}
]
}Undo a previous end-user merge: reads the merge ledger and re-points every FK row (events, insights, tasks, …) back to its original end-user, un-tombstoning the folded-in sources. Idempotent — undoing an already-reverted merge is a no-op. Use to correct a wrong identity merge (merges stay reversible for 30 days). Pass the merge event_id to undo (from the identity merge history); event_id is required.
| event_id | string | required | Id of the merge event to undo, from the identity merge history. |
{
"type": "object",
"properties": {
"event_id": {
"type": "string",
"description": "Id of the merge event to undo, from the identity merge history."
}
},
"required": [
"event_id"
],
"examples": [
{
"event_id": "uuid"
}
]
}README not available yet.
Hosted server - connect over the network, no local install.
https://platform.aioproductos.com/api/mcpclaude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://platform.aioproductos.com/api/mcp"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.