servers / com-aioproductos-mcp
com.aioproductos/mcp
communitystreamable_httpremotewrite capablehealthy
AIOProductOS spine over MCP — customers, revenue, feedback, work, analytics on one typed record.
01Tools · 38
How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.
| Tool | Risk | Side effects | Approval |
|---|---|---|---|
| get_pm_playbook 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 this before planning or prioritising. | read | false | unknown |
| whoami Show the connected AIOProductOS identity (org, member) AND the org's products (id, name, is_primary). For a multi-product org, read 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. | read | false | unknown |
| pm_meta List the org's PM lists, statuses, members, and features — use to resolve names to ids before create/update. | read | false | unknown |
| get_product_brain 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. Optional product_id; omit for the primary product. | read | false | unknown |
| get_weekly_signal_memo 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 | false | unknown |
| get_roadmap_drift 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 | false | unknown |
| get_customer_360 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. The money + people + voice join on one record — use before answering anything about a specific account. | read | false | unknown |
| analyze_nps 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). | unknown | unknown | unknown |
| analyze_nrr 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 | false | unknown |
| analyze_funnel Build a conversion funnel from the product's own events. Pass `steps` as an ordered list of event names (2+): distinct users per step, conversion, drop-off. Omit `steps` to get the menu of event names first. Optional product_id and window_days (default 30). | read | false | unknown |
| get_retention Weekly cohort retention for the product: users grouped by first-seen week, with the share returning each week after. Optional product_id and window_days (default 56 = 8 weekly cohorts). | read | false | unknown |
| analyze_paths Trace what users do AFTER a start event — the journey flow (Sankey) from the product's own events. Pass `start` to anchor on an event, or omit for the most common start. Optional product_id and window_days (default 30). | unknown | unknown | unknown |
| list_tasks List tasks in the org. Optional filters: status_id, list_id. | read | false | unknown |
| get_task Get one task with its comments and assignees. | read | false | unknown |
| create_task Create a task. Omitting list_id uses the org's first list. feature_id / insight_id link it to the spine; sprint_id schedules it into a sprint (resolve via list_sprints). | write | true | unknown |
| review_artifact 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. Persists the review. Resolve target_id via pm_meta / the analytics surfaces. One small LLM call. | read | false | unknown |
| list_artifact_versions 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. Use it to see how a feature/experiment/page's review changed over time before reverting to an earlier one. Read-only. | read | false | unknown |
| revert_to_version Restore an earlier artifact version (F5) to current — the current version is flipped to 'reverted' (kept for the learning signal) and the chosen version becomes current again. version_id is the version you want to RESTORE (from list_artifact_versions). Optional reason. | unknown | unknown | unknown |
| update_task Update a task's fields (status, priority, title, description, feature, insight, sprint, assignees). | write | true | unknown |
| comment_on_task Add a comment to a task. | write | true | unknown |
| capture_insight Write a piece of customer feedback to the spine (the agent's own hand, not just reading). Fires the same insight.created webhook a manual capture does. Tie it to the account (account_id) and feature (feature_id) when known; kind='opportunity' for a prioritisable ask. | unknown | unknown | unknown |
| list_conversations List support-chat conversations in the inbox (open + snoozed by default; pass status='all' to include closed). Optional product_id to scope to one product. | read | false | unknown |
| get_conversation Read one support conversation: the visitor + the full message thread (oldest first). | read | false | unknown |
| list_insights Search the captured insight backlog (voice of customer) — the read twin of capture_insight. Filters: status, kind (insight|opportunity), feature_id, account_id, product_id, and free-text q over title+body. Newest first; limit default 50, max 200. | read | false | unknown |
| list_features 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). Optional product_id and free-text q over name+key. | read | false | unknown |
| list_objectives 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. Optional product_id. | read | false | unknown |
| list_experiments Experiments — hypothesis, metric, target, state, verdict, and the decision that came out. See what's being tested and what it concluded. Optional product_id and state filters. | read | false | unknown |
| list_releases The release log — version, changelog, and ship date, newest first. Answer 'what did we ship recently?'. Optional product_id. | read | false | unknown |
| list_pages List the in-product docs / PRDs (Pages) on the spine — titles + ids, no content. Use get_page to read one. Optional product_id. | read | false | unknown |
| get_page Read one Page (doc / PRD) with its full content. | read | false | unknown |
| get_codebase_map The auto-generated codebase brain map: a summary, the module/node/edge counts, when it was generated, and the module labels — ground 'where in the code does X live?'. Per product (primary by default, or product_id). | read | false | unknown |
| list_sprints Sprints — name, goal, state, and window, newest first. See the delivery cadence (active + recent). Optional state filter (e.g. 'active'). | read | false | unknown |
| list_channels List the team Comms channels the connected member belongs to (membership-scoped). Use read_channel to read one. | read | false | unknown |
| read_channel Read a Comms channel's recent messages (the member must be a channel member). Optional limit. | read | false | unknown |
| list_bookings Upcoming confirmed bookings on the org's scheduling. Pass include='all' for full history. | read | false | unknown |
| get_device_candidates Clusters of ≥2 end_users seen on the same device. 'anon_bridge' (high confidence: anonymous + identified) or 'device_shared' (low confidence: review-only). | read | false | unknown |
| merge_end_users Merge source end-users into a target. All FK rows (events, insights, tasks, …) are re-pointed; sources are tombstoned. Reversible for 30 days. | write | true | unknown |
| unmerge_end_users Revert a previous end-user merge. Reads the ledger to restore all rows to their original end-user assignment. | unknown | unknown | unknown |
02Install & source
https://platform.aioproductos.com/api/mcp
remote_url03Access granted
Manage tasks & tickets · write
The access this server can exercise, inferred from its verified tools — not a declared OAuth scope.
05Provenance & freshness
sourcesOfficial MCP Registry [p1]
last_checked2026-07-10 21:21Z
next_check2026-07-12 21:20Z
cadenceevery 48h
verifiedtools_list:passed handshake:passed metadata:passed
index_statusindex — 5 unique facts >= 5
06Badge
Add the “as seen on MCPExplorer” badge to your README. 
[](https://mcpexplorer.com/servers/com-aioproductos-mcp)
Next step
This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.
Explore loadouts →