Orshot for AI agents
Orshot generates images, PDFs, and videos from design templates and manages brand assets and templates for a workspace. Marketing and design teams use it to produce on-brand visuals automatically. 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.
What agents do in Orshot.
Render an image from a template
Generate a branded image from a studio template filled with campaign-specific text.
Check available templates read-only
List studio templates to pick the right one before rendering a new asset.
Add a brand color
Register a new brand color in the workspace so future renders stay on-brand.
8 Orshot actions, graded by risk.
Every Orshot action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- orshot.get_profileGet Profile
- orshot.list_brand_assetsList Brand Assets
- orshot.get_studio_templateGet Studio Template
- orshot.list_social_accountsList Social Accounts
- orshot.list_studio_templatesList Studio Templates
write
2Create and change things. Allow, or ask the user first.
- orshot.add_brand_colorAdd Brand Color
- orshot.render_studio_templateRender Studio Template
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- orshot.delete_brand_colorDelete Brand Color
Orshot in three steps.
- 01Your users connect OrshotThey add their Orshot api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “add Brand Color” can wait for the user, and “delete Brand Color” can be denied outright.
- 03Any agent can actYour agent calls Orshot through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('orshot', { read: 'allow', write: 'ask', // add_brand_color destructive: 'deny', // delete_brand_color }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Orshot connects.
Users add their Orshot 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 Orshot 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
Use Orshot from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Orshot and Arc0, answered.
Can I use Orshot with Claude, ChatGPT or Cursor?
Yes. Connect Orshot 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 Orshot actions you allow.
How do users connect Orshot?
Users add their Orshot 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.
Which Orshot actions can my agent take?
8 in total: 5 read, 2 write and 1 destructive, such as “add Brand Color”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Orshot?
Yes. Actions like “delete Brand Color” 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.
Can my own backend call Orshot too?
Yes. The same Orshot connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Orshot into your agent.
Your users connect Orshot once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan