← All integrations

Placid MCP server

26 operations0 webhooks

Creative automation with Placid - render templates to images, PDFs and videos, plus the template, collection, media and font operations behind them.

Use Placid in Claude, ChatGPT, Cursor or another MCP client

Connect Placid once in Corsair, then add one MCP address to your agent.

Connect Placid
Setup steps for Claude, ChatGPT, Cursor and Claude Code

Building your own app on the Corsair SDK? Get API keys

Try Placid with your agent

Connect Placid, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in Placid on my account, then run one read-only example and show me the result.

Runs once, when you ask

Placid tools and triggers

Tools are what your agent can do in Placid through Corsair's MCP server. Triggers are the Placid events a routine can start from.

Collections

  • CreateWrite

    Create a collection, such as one per customer of your SaaS, holding up to 500 templates

    collections.create

  • DeleteDestructive

    Permanently delete a collection. The templates inside it are not deleted

    collections.delete

  • GetRead-only

    Read one collection and the template UUIDs it holds

    collections.get

  • ListRead-only

    List template collections, either all at once or cursor-paged with `per_page`

    collections.list

  • UpdateWrite

    Change a collection: replace its whole template list with `template_uuids`, or add and remove individual templates

    collections.update

Fonts

  • CreateWrite

    Upload a ttf, otf, woff or woff2 font from a public URL. `terms_accepted` must be true. The returned `uuid` is the value to set as the `font` property on a text layer

    fonts.create

  • DeleteDestructive

    Delete a custom font. Fails with 409 when a template still uses it unless `force` is set, which leaves those templates on the default font

    fonts.delete

  • GetRead-only

    Read one custom font by its `uuid`

    fonts.get

  • ListRead-only

    List the custom fonts in the project, optionally including legacy account-wide fonts

    fonts.list

  • UpdateWrite

    Rename a custom font. The file itself cannot be replaced: upload a new font instead

    fonts.update

Templates

  • CreateWrite

    Create an empty template, or duplicate an existing one with `from_template`, optionally adding it to collections

    templates.create

  • DeleteDestructive

    Permanently delete a template

    templates.delete

Connect Placid to Claude, ChatGPT or Cursor

  1. 1

    Connect Placid in Corsair

    Add your Placid API key once in Corsair. Corsair stores the credential encrypted and makes the Placid API calls for your agent, so it never goes into a prompt or a config file. Connect Placid

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Placid. On a ChatGPT personal plan, connect Placid here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Placid's read and write operations run right away and its 6 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/placid, add the Placid plugin, and connect with an API key. Then call methods like corsair.placid.api.collections.create() from your app. Corsair keeps each tenant isolated.

Yes. Placid requires an API key from your Placid account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit Placid, GitHub, Notion, Stripe, and the rest. Trigger Placid from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for creative automation with Placid - render templates to images, PDFs and videos, plus the template, collection, media and font operations behind them. Common builds include sync jobs, admin tooling, and agents that call Placid APIs from your backend.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Placid API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/placid in the open repo. When Placid ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your Placid data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Placid data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put Placid on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 6 destructive Placid operations. You can change a link's mode at hub.corsair.dev/me.