Placid for AI agents
Placid is a creative automation toolkit for generating images, PDFs, and videos from custom templates. Marketing teams use it to produce on-brand visuals programmatically. 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 Placid.
Check available templates
List templates read-only to find the right design before generating a new asset.
Update a template's design
Adjust a template's layout or fields so future renders reflect a brand refresh.
Delete a template with approval
Remove an outdated template only after confirming no campaign still relies on it.
11 Placid actions, graded by risk.
Every Placid 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.
- placid.get_templateGet Template
- placid.get_collectionGet Collection
- placid.list_templatesList Templates
- placid.get_collectionsGet Collections
- placid.list_nl_templatesList NL Templates
write
4Create and change things. Allow, or ask the user first.
- placid.create_templateCreate Template
- placid.update_templateUpdate Template
- placid.create_collectionCreate Collection
- placid.update_collectionUpdate Collection
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- placid.delete_templateDelete Template
- placid.delete_collectionDelete Collection
Placid in three steps.
- 01Your users connect PlacidThey add their Placid api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Template” can wait for the user, and “delete Template” can be denied outright.
- 03Any agent can actYour agent calls Placid through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('placid', { read: 'allow', write: 'ask', // create_template destructive: 'deny', // delete_template }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Placid connects.
Users add their Placid 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 Placid 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 Placid from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Placid and Arc0, answered.
Can I use Placid with Claude, ChatGPT or Cursor?
Yes. Connect Placid 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 Placid actions you allow.
How do users connect Placid?
Users add their Placid 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 Placid actions can my agent take?
11 in total: 5 read, 4 write and 2 destructive, such as “create Template”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Placid?
Yes. Actions like “delete Template” 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 Placid too?
Yes. The same Placid connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Placid into your agent.
Your users connect Placid once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan