About Caisy MCP by usefulapi
A hosted MCP server for read-only access to one Caisy project's blueprints, documents, and media assets. It supports GraphQL queries as well as tools for listing project queries, documents, and assets.
Key features
- 01Run read-only GraphQL queries
- 02List project read queries
- 03List documents by blueprint
- 04List media assets
Use cases
- 01Query project content through GraphQL
- 02Browse documents for a blueprint
- 03Find media assets in a project
MCP support
Exposes read-only Caisy project queries and content-listing tools to MCP clients through a hosted remote endpoint. Users provide a project ID and API key during sign-in; credentials are stored per user.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://caisy.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-caisy https://caisy.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-caisy":{"type":"http","url":"https://caisy.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-caisy":{"type":"http","url":"https://caisy.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-caisy":{"type":"http","url":"https://caisy.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-caisy":{"serverUrl":"https://caisy.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMECaisy MCP by usefulapi
Use your Caisy account from Claude, Cursor, or any MCP client. Reads blueprints, documents and media assets of one Caisy project through read-only GraphQL queries. Hosted, no local install: connect with your own credentials.
Live endpoint: https://caisy.usefulapi.io/mcp · Homepage: https://usefulapi.io
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://caisy.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http caisy https://caisy.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"caisy": {
"url": "https://caisy.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Caisy credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/caisy/
On first connect you provide your Caisy project ID (the UUID in your GraphQL endpoint URL) and your Caisy API key (Settings → Development → API Keys). The server validates it and stores it per user. No keys go in config files.
Tools
| Tool | Type | What it does |
|---|---|---|
caisy_run_query | read | Run a read-only GraphQL query |
caisy_list_queries | read | List the project's read queries |
caisy_list_documents | read | List documents of a blueprint |
caisy_list_assets | read | List media assets |
caisy_usage_status | meta | Usage status (free-tier meter) |
caisy_request_feature | meta | Request a missing feature |
caisy_upgrade | meta | Upgrade to Pro (unlimited*) |
caisy_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro (per user) | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with caisy_upgrade (it returns a Stripe Checkout link). Cancel any time with caisy_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running caisy_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.