aioproductosSAFE
Official AIOProductOS plugin for Claude Code — connect your workspace (39 MCP tools) and run evidence-backed weekly product triage
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://glama.ai/mcp/servers/AIOProductOS/claude-plugin)
[](https://glama.ai/mcp/connectors/com.aioproductos/mcp) [](https://registry.modelcontextprotocol.io/v0/servers?search=com.aioproductos)
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-triage` skill — 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
106467f55ba8OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add aioproductos-mcpb-server --env PRODUCTOS_TOKEN=${PRODUCTOS_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"aioproductos-mcpb-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"PRODUCTOS_TOKEN": "${PRODUCTOS_TOKEN}"
}
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Board | read | The org |
daily | read | Daily PM briefing — your plate, blockers, and the one thing to do next. |
standup | read | Board standup — what moved, what |
triage | read | Triage — turn fresh customer signal into prioritized, spine-linked work. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
- **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 i
desktop-extension/server/generated/apps.js
Gates applied: no_behavioural_pass.
106467f55ba8full audit observations/trust-audit/mcp-server/aioproductos__claude-plugin.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 106467f55ba8 | SAFE | B | 89 | first audit |
Questions
What is the aioproductos MCP server?
Official AIOProductOS plugin for Claude Code — connect your workspace (39 MCP tools) and run evidence-backed weekly product triage
What tools does aioproductos expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is aioproductos safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does aioproductos need?
It reads PRODUCTOS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does aioproductos run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as aioproductos-mcpb-server at 0.18.0.
How current is this page?
The grade is for one exact copy of the source (106467f55ba8), read on 2026-10-11. The repository is watched and re-audited when it changes.