Sideshow for AI agents

Sideshow is a collaborative visual workspace where agents publish, update, and discuss posts containing interactive content. Teams use it to share and comment on rich work in progress. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Developer toolsAPI keyMCP + REST
AUDIT LOG · SIDESHOWPOLICY: acme-support
09:41:07 · claude · u_8f2read
sideshow.list_kits
List Kits✓ allowed · 212ms
09:41:08 · claude · u_8f2read
sideshow.get_post
Get Post✓ allowed · 164ms
09:41:09 · claude · u_8f2write
sideshow.create_comment
Create Comment✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
sideshow.delete_post
Delete Post✕ blocked · policy: deny
EVERY SIDESHOW CALL, ON THE RECORD
01 · USE CASES

What agents do in Sideshow.

01

Publish a post to the workspace

Publish a new post with interactive content for the team to view and react to.

02

Review existing posts first

List current posts before publishing, to avoid duplicating something already shared.

03

Confirm before deleting a comment

Check a comment's thread and get confirmation before deleting it from a post.

02 · ACTIONS

10 Sideshow actions, graded by risk.

Every Sideshow action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • sideshow.get_post
    Get Post
  • sideshow.list_kits
    List Kits
  • sideshow.list_posts
    List Posts
  • sideshow.list_comments
    List Comments
  • sideshow.list_sessions
    List Sessions

write

3

Create and change things. Allow, or ask the user first.

  • sideshow.update_post
    Update Post
  • sideshow.create_comment
    Create Comment
  • sideshow.publish_post
    Publish Post

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • sideshow.delete_post
    Delete Post
  • sideshow.delete_comment
    Delete Comment
03 · HOW IT WORKS

Sideshow in three steps.

  1. 01Your users connect SideshowThey add their Sideshow api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Comment” can wait for the user, and “delete Post” can be denied outright.
  3. 03Any agent can actYour agent calls Sideshow through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('sideshow', {
  read: 'allow',
  write: 'ask',        // create_comment
  destructive: 'deny',  // delete_post
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Sideshow connects.

Users add their Sideshow api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Sideshow connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Sideshow from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Sideshow and Arc0, answered.

Q01

Can I use Sideshow with Claude, ChatGPT or Cursor?

Yes. Connect Sideshow to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Sideshow actions you allow.

Q02

How do users connect Sideshow?

Users add their Sideshow api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Sideshow actions can my agent take?

10 in total: 5 read, 3 write and 2 destructive, such as “create Comment”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Sideshow?

Yes. Actions like “delete Post” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Sideshow too?

Yes. The same Sideshow connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Sideshow into your agent.

Your users connect Sideshow once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan