AIOProductOS MCP
MCP serverDatabases & dataConnect your AI to AIOProductOS, a platform that keeps revenue, feedback, work, and analytics on one customer record. Once added, your AI can look up any customer's full picture and run product analyses like NPS, retention, funnels, and roadmap alignment without leaving the conversation. The integration includes 71 tools across 3 apps, 35 of them verified.
Use AIOProductOS MCP in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add AIOProductOS MCP and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use AIOProductOS MCP to get pm playbook
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Details
Available today. Use it from your connected AI after setup. It ran on Ahel's own infrastructure and offers 35 tools.
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
After adding it, ask your AI to show the connected organization and its products to confirm the link, then request a snapshot of your product or a customer's full record. A built-in playbook explains how to operate as a product manager on AIOProductOS.
What your AI can do with it
- Pull a complete customer profile with subscription, revenue, and usage details
- Get a weekly memo of customer signal clustered into themes
- Compare planned versus shipped features with a roadmap drift score
- Calculate NPS and net revenue retention, weighted by revenue
- Build conversion funnels and weekly cohort retention from product events
- Trace what users do after a start event
Install AIOProductOS MCP
The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user aioproductos-mcp 'https://platform.aioproductos.com/api/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://platform.aioproductos.com/api/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=aioproductos-mcp&config=eyJ1cmwiOiJodHRwczovL3BsYXRmb3JtLmFpb3Byb2R1Y3Rvcy5jb20vYXBpL21jcCJ9Open the link and Cursor adds the server at that address.
ChatGPT
https://platform.aioproductos.com/api/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add aioproductos-mcp --url 'https://platform.aioproductos.com/api/mcp'Run it once, then sign in with codex mcp login aioproductos-mcp if the server asks for an account.
From the project's README
As published by aioproductos/claude-plugin in README.md.
Connect your AIOProductOS workspace to Claude Code and work your whole product from chat — feedback, revenue, tasks, releases, analytics, and code activity joined on one customer record.
One install gives you:
- The workspace connection — the AIOProductOS remote MCP server: 71 tools over the product spine, and it doesn't just read. It's a fully autonomous PM surface — read the spine and write to it across the whole strategy-to-delivery ladder: capture and vote on ideas, promote them into features, set initiatives and objectives & key results, plan sprints and releases, run experiments, log decisions, write pages, and create/update/delete tasks — plus post to team channels, capture insights, and merge/unmerge people. OAuth sign-in, no API keys.
/aioproductos:triage— Monday-morning product triage: surfaces the top 3 customer-evidenced insights, scores them transparently from real revenue and usage, and (after you confirm) creates the tasks, assigns a named AI teammate, and schedules them into the next sprint.- The
aioproductos-triageskill — the full triage doctrine, available whenever you ask "what should we work on next?"
What you can do
Read the spine — customer 360, product brain, weekly signal memo, roadmap drift; analytics: NPS, NRR, funnels, retention, path analysis; list ideas, initiatives, tasks, features, objectives, sprints, releases, pages, experiments, insights, conversations, channels, bookings, identity merges, codebase map.
Write to the spine — no jumping back to the web UI:
- Discovery — capture ideas, vote on them, promote an idea into a feature
- Strategy — create/update initiatives, objectives and key results, decisions, experiments
- Roadmap — create/update features, releases, pages
- Delivery — create/update tasks, comment, create/update sprints
- Customers & comms — capture insights, post to channels, merge/unmerge end users
- AI artifacts — review artifacts, revert to a prior version
Everything is scoped to your organization and your role's permissions, and writes go through the same guardrails as the app.
Writes someone else can see. Three groups reach beyond your own workspace, so
they're worth knowing about before you connect: reply_to_conversation,
add_note and resolve_conversation act on your support inbox and a visitor
sees the reply; post_to_channel and reply_in_channel post to team channels as
you; cancel_booking and reschedule_booking change a booked meeting and notify
the guest.
One destructive tool. delete_task is permanent, cascades to subtasks, and
has no undo — so it requires confirm: "DELETE" alongside the task id. A task id
alone can never trigger it; the assistant has to ask you first. Nothing else
deletes anything.
Interactive apps
Three tools render a working interface in the conversation rather than a wall of JSON (MCP Apps, SEP-1865). They aren't screenshots — each one calls back into this same MCP:
| Ask for | You get | What it writes |
|---|---|---|
list_tasks | Board — your tasks grouped by status, ranked by priority | change a status → update_task |
get_weekly_signal_memo | Weekly signal — this week's themes with the evidence behind each | a theme → create_task, linked to its feature |
analyze_funnel | Funnel — conversion per step with the live MRR behind each one | read-only |
Hosts that support MCP Apps (Claude, ChatGPT, VS Code, Goose and others) render them inline. Everywhere else the tools return exactly the text they always did — the app is an enhancement, never the only copy of the answer.
Install
/plugin marketplace add AIOProductOS/claude-plugin
/plugin install aioproductos@aioproductos
On first use, the AIOProductOS connector will prompt you to sign in with your workspace account and approve access. All data is scoped to your organization and your role's permissions.
Requirements
An AIOProductOS workspace (aioproductos.com). New organizations get a 14-day onboarding runway on their own data, and every plan carries a 30-day money-back guarantee. Your AI usage is never metered — flat plans, no credit meters.
What the triage looks like
This week's triage — top 3 (evidence-backed). Confirm before I create them.
# | Insight (source) | Proposed task | Score
--+-------------------------------+--------------------------+------
1 | "Need SAML" — 3 accts, $4.2k | SSO/SAML for enterprise | 2.4
2 | Onboarding drop 38% (funnel) | Shorten signup form | 240
3 | Churned acct cited exports | CSV export on reports | 4.0
Want me to create, assign (Ada · Backend AI), and schedule all 3 into Sprint W27?
Every number traces to a record on the spine — accounts, MRR, funnel steps — not a planning-poker vibe. Effort stays a human call, and nothing is written until you confirm.
Other ways to connect
- Any MCP host: custom connector URL
https://platform.aioproductos.com/api/mcp - CLI/stdio:
npx @aioproductoscom/mcp - Docs: aioproductos.com/mcp
Support
Questions, feedback, feature requests: office@aioproductos.com — a human founder answers every email.
License
MIT — see LICENSE. The plugin is free; it drives a paid AIOProductOS workspace.
Tools it gives your AI (35)
| Tool | What it does |
|---|---|
| get_pm_playbook | How to operate as a product manager on AIOProductOS. No arguments and no side effects — returns the same operating guide as plain text every call (deterministic): how to ground in the product brain... |
| whoami | 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. |
| pm_meta | 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). |
| get_product_brain | A grounded snapshot of the org's product so YOU can reason about it. Returns one JSON object with: revenue + top paying accounts (ranked by MRR), web + product analytics headline metrics, the... |
| 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... |
| 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... |
| 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. |
| analyze_nps | NPS for the product: the standard −100…100 score AND revenue-weighted NPS (each respondent weighted by their account MRR), plus detractor accounts ranked by MRR-at-risk (highest first). |
| 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 (ranked, highest loss first). |
| analyze_funnel | Build a conversion funnel from the product's own events: distinct users per step, step-to-step conversion %, and drop-off, evaluated in the exact order you pass. |
| get_retention | Weekly cohort retention for the product: users grouped by first-seen week (one row per cohort, newest last), with the share still active each subsequent week — a lower-triangular grid. |
| analyze_paths | Trace what users do AFTER a start event — the journey flow (Sankey) from the product's own events. |
| list_tasks | 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. |
| get_task | 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... |
| list_initiatives | List the org's initiatives — the strategic layer between goals and features (goal → initiative → feature → epic → release). |
| list_ideas | List the org's ideas — the native, votable idea backlog — ranked by vote count (highest first). Each returns its title, status, vote count, author, and the feature it was promoted to (if any). |
| list_decisions | List the org's logged decisions — title, rationale, status, and any linked feature/release/objective — newest first. Returns an empty list when none. |
| 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. |
| list_conversations | 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. |
| get_conversation | 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. |
| list_insights | 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. |
| 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). |
| list_objectives | List the org's OKRs. Returns an array of objectives, each with its key results and live progress (0..1 between start and target), so you can prioritise toward what the team is actually trying to move. |
| list_experiments | List product experiments. Returns an array where each experiment carries its hypothesis, the metric it moves, the target, its current state, and — once concluded — the verdict and the decision that... |
| list_releases | List shipped releases. Returns an array, newest first, where each release carries its version, changelog, and ship date. Read-only; empty when nothing has shipped. |
| list_pages | List the in-product docs / PRDs (Pages) on the spine. Returns an array of pages with title + id only — no content, so it stays cheap to scan. Read-only; empty when none exist. |
| get_page | Read one Page (doc / PRD) by id and return its full content. Read-only. Resolve the id first with list_pages — never guess it. |
| get_codebase_map | 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. |
| list_sprints | Sprints — name, goal, state, and window, newest first. Read-only; returns the matching sprints, empty when none exist. |
| list_channels | 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. |
| read_channel | 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. |
| list_bookings | Upcoming confirmed bookings on the org's scheduling. Read-only; returns the bookings, empty when none are scheduled. Pass include='all' for full history. |
| get_device_candidates | 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). |
| list_identity_merges | List the org's end-user merge history. Returns an array of merge events, newest first, where each carries its event id, kind (merge or unmerge), the target and source end-user ids, the reason, who... |
| join_your_stack | Join the caller's OWN product data — their work items, their customers, their feature requests — and return which paying customers are waiting on which open work, ranked by the revenue behind each. |
Signals
- Last commit
- Jul 2026
- Weekly downloads
- 47
- Tools captured
- 35
Advanced
- Delivery
- AIOProductOS MCP MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
com-aioproductos-mcp- Source
- github.com/aioproductos/claude-plugin
- Hosted endpoint
https://platform.aioproductos.com/api/mcp
github.com/aioproductos/claude-plugin
More in Databases & data
MCP server
More in Databases & dataQuantRisk
MCP server · 78degrees
More in Databases & dataPostHog MCP Server
MCP server · posthog
More in Databases & dataAppfigures
MCP server · appfigures
More in Databases & dataRun402
MCP server · kychee-com
More in Databases & dataagent-native-analytics
MCP server · builderio
More in Databases & data