shareout-integrationsSAFE
Publish agent-made pages, collect feedback, and revise at the same link. Shareout plugins, skills, and MCP connections.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your agent made it. Share it out.
Share work from your AI workspace with clients, contractors and collaborators outside it—even people who do not use AI themselves.
Your agent helped make it. The people reviewing it do not need an agent. Send an HTML proposal, report or interactive prototype as a browser link. Recipients can view and try the page without joining your Claude, Codex or Cline workspace. Grant commenting access separately when you want feedback; your agent can read it and revise the work at the same address.
Try a shared page · Connect your agent · Templates
This repository contains the public plugin, skill, and connection configurations. The hosted service and standalone CLI are maintained separately. Repository installation is available independently of curated directory approval; see distribution status.
Claude Code
claude plugin marketplace add geland/shareout-integrations claude plugin install shareout@shareout
The plugin includes the hosted MCP connection and a short publishing skill. Connect your Shareout account through the host's OAuth flow. In Claude web or desktop, you can also add https://shareout.io/mcp as a custom connector where your plan supports it.
Codex
codex plugin marketplace add geland/shareout-integrations codex plugin add shareout@shareout
For an MCP-only connection, merge configs/codex.toml into your Codex configuration and run codex mcp login shareout. This repository is a community-installable source; it does not imply approval in the public ChatGPT/Codex directory.
Gemini CLI
gemini extensions install https://github.com/geland/shareout-integrations
The extension bundles the hosted MCP connection and the Shareout skill. Start Gemini and run /mcp auth shareout to connect your account. The skill loads workflow deta
61b69cd6cd75OBSERVED · 2026-10-11Trust 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 | WARN |
| 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)
streamable-http
Gates applied: no_behavioural_pass.
61b69cd6cd75full audit observations/trust-audit/mcp-server/geland__shareout-integrations.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 | 61b69cd6cd75 | SAFE | B | 89 | first audit |
Questions
What is the shareout-integrations MCP server?
Publish agent-made pages, collect feedback, and revise at the same link. Shareout plugins, skills, and MCP connections.
Is shareout-integrations 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 shareout-integrations need?
No credential environment variables were found in its source, so it appears to need none.
How does shareout-integrations run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (61b69cd6cd75), read on 2026-10-11. The repository is watched and re-audited when it changes.