Cloudsmith for AI agents

Cloudsmith manages and distributes software packages across teams, giving engineering a controlled, private registry instead of relying on public package feeds. 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 + RESTcloudsmith.com
AUDIT LOG · CLOUDSMITHPOLICY: acme-support
09:41:07 · claude · u_8f2read
cloudsmith.list_organizations
List Organizations✓ allowed · 212ms
09:41:08 · claude · u_8f2read
cloudsmith.get_quota
Get Quota✓ allowed · 164ms
EVERY CLOUDSMITH CALL, ON THE RECORD
01 · USE CASES

What agents do in Cloudsmith.

01

Search for a package

Search across repositories for a specific package version before pulling it into a build.

02

Check a repository's vulnerabilities

List known vulnerabilities in a repository before approving a package for wider use.

03

Check usage quota

Check current quota and rate limits before scheduling a large batch of package pulls.

02 · ACTIONS

10 Cloudsmith actions, graded by risk.

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

read

10

Look things up. Allowed by default.

  • cloudsmith.get_quota
    Get Quota
  • cloudsmith.get_package
    Get Package
  • cloudsmith.get_repository
    Get Repository
  • cloudsmith.get_rate_limits
    Get Rate Limits
  • cloudsmith.search_packages
    Search Packages
  • cloudsmith.get_current_user
    Get Current User
  • cloudsmith.search_audit_log
    Search Audit Log
  • cloudsmith.list_organizations
    List Organizations
  • cloudsmith.search_repositories
    Search Repositories
  • cloudsmith.list_repository_vulnerabilities
    List Repository Vulnerabilities

write

0

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

  • No write actions.

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Cloudsmith in three steps.

  1. 01Your users connect CloudsmithThey add their Cloudsmith api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Cloudsmith 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('cloudsmith', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# 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 Cloudsmith connects.

Users add their Cloudsmith 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 Cloudsmith 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 Cloudsmith from any agent.

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

Cloudsmith and Arc0, answered.

Q01

Can I use Cloudsmith with Claude, ChatGPT or Cursor?

Yes. Connect Cloudsmith 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 Cloudsmith actions you allow.

Q02

How do users connect Cloudsmith?

Users add their Cloudsmith 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 Cloudsmith actions can my agent take?

10 in total: 10 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Cloudsmith?

Yes. Allow read actions and deny writes in the Cloudsmith policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Cloudsmith too?

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

Get started

Plug Cloudsmith into your agent.

Your users connect Cloudsmith 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