Add the server to your client
Jackdaws runs as a remote Model Context Protocol server behind OAuth. Adding it takes one URL and one credential. What happens after that depends on your client: whether it can lend the server a model, and whether it authenticates as itself or as a shared connector.
New to this? The step-by-step setup walks you through it one step at a time, for the tool you use.
One URL, every client
https://mcp.jackdaws.ai/mcp
A trimmed surface lives at /mcp/ide for editors that cap how many tools they will enable at once. Same credential, same verifiers, a shorter list.
Inspect the surface first
Tool and prompt listings stay open. Point any MCP client at the server, authorize, and you can read every tool name, description, and schema without a subscription. Calls are the gated part.
An unsubscribed call returns a payment-required error, not an empty result. A lookup the server cannot complete returns a distinct retryable error instead, so a database blip never reads as a lapsed subscription.
claude.ai, Claude Code, Antigravity, or your own setup
Each one is covered below, with what it gets and what it does not.
Pick the path that matches your client
claude.ai connector
Teams working in the browser
- Add the server as a custom connector.
- Authorize in the browser. Registration is automatic, so there is no client id to paste.
- Listings open immediately; calls need an active subscription.
- Model
- No sampling. Generative calls return a generation contract your own conversation executes, closed by a deterministic validation tool.
- Identity
- Your own sign-in. The ledger counts the person, and the subscription is yours.
Claude Code / Desktop
Engineers with a client that lends its model
- Add the server to your MCP client configuration.
- Authorize in the browser on first call.
- Run sampling_probe once to confirm which Layer-2 execution path you land on.
- Model
- Sampling. The generative agents run on the model already in your session, so the model bill stays yours.
- Identity
- The connecting credential, or a per-user credential when you have one.
Google Antigravity
The agy CLI and the Antigravity IDE
- Keep your subscription's client id and secret in your own secret store.
- Run the connect script, or write the server entry into Antigravity's MCP config yourself with an Authorization header.
- Reload MCP servers. Tokens are short-lived, so re-run when calls start returning 401.
- Model
- No sampling. Generative calls return a generation contract for the model driving Antigravity to execute.
- Identity
- The API key you connected with, billed to the account that created it.
CI / custom harness
Pipelines and per-user metering
- Create an API key in your account — a client id and a secret, shown once.
- Hold the client id and secret in your own secret store.
- Exchange them for a bearer token and call the server directly.
- Model
- Sampling when your harness advertises it, the generation contract otherwise.
- Identity
- One key per pipeline or per machine, each billed to the account that made it. Revoke it in your account when it is done.
What the hosted server cannot do
It cannot see your working tree
The server runs in its own container with no shared mount, so an absolute path from your laptop does not resolve there. Send the skill files inline instead: the verifiers on the remote allowlist accept the content itself and run against a bounded per-call sandbox.
Whole-repository work stays local
Audits that sweep a whole tree, a registry, or your session transcripts need filesystem access the hosted server does not have. The CLI runs these locally against your own repository, on your machines.
Subscribe and connect
Sign in, pay, and land in your account. Follow the steps for your client above — the browser clients sign in with your email, and your account creates API keys for the rest.