Skip to main content
Wire Claude Code to the hosted ish MCP server so the agent can call ish tools (study_run, ask_run, person_generate, and the rest) from your terminal. The server lives at https://mcp.ishlabs.io/mcp, speaks streamable HTTP, and signs you in over OAuth on first connect, so no token is written to your config.
You need an ish account. If you do not have one, get ish free first. The OAuth step signs Claude Code in as you.

​
Connect

Pick one path. Both write the same ish server block to Claude Code’s user-scope config at ~/.claude.json and leave OAuth to the server.
Add the server at user scope:
claude mcp add --transport http --scope user ish https://mcp.ishlabs.io/mcp
Claude Code discovers ish’s OAuth metadata, registers itself, opens your browser to sign in, and stores the resulting token. User scope (--scope user) makes ish available in every project on this machine; drop to --scope project to write a shared .mcp.json in the current repo instead.
Use https://mcp.ishlabs.io/mcp with no trailing slash. The /mcp/ form triggers a redirect (HTTP 307) that some clients will not follow on a POST, leaving the agent with an empty tool list.

​
Verify

Reconnect or restart Claude Code so it runs the OAuth flow, then approve the sign-in in your browser. Confirm the tools are live with a read-only question, which draws no credits: 
Use the ish tools to confirm who I am and list my workspaces.
Claude Code calls workspace_get (read-only) and reports your workspaces. A brand-new account returns an empty list, which is still a successful connection. Claude Code reads MCP resources, so it can also surface ish://identity/me, the decoded identity for the session.
Claude Code returns a workspace list (or an explicit empty list) instead of “no ish tools available”. The OAuth sign-in landed and the tools are live.
If the agent reports no ish tools, the OAuth step did not complete. Reconnect and approve the sign-in, then ask again.

​
Read your first reaction

Run a study that already lives in your workspace and read back what a simulated person made of it. Tell Claude Code: 
Find a study in my workspace, run it for a few people, and tell me what they noticed.
The agent works through ish’s tools:
1

Discover a study

It calls study_get with your workspace_id to list studies and pick one.
2

Run it

It calls study_run with a small audience and wait=True, which blocks until every simulated person reaches a terminal state.
3

Read the reactions

It calls study_get with view="summary" and reports the journey: what people noticed, where they got stuck, and the reasoning behind each reaction.
You get a narrative reaction with the reasoning attached, not a single score. That is the loop: simulate a visit, read what landed, decide what to change.
No study in this workspace yet? Ask Claude Code to create one first (“create a study that points simulated readers at this URL and asks what they noticed”), then run it. study_create and study_run cover both. For the full walkthrough, see Quickstart: connect an AI agent.

​
Point a study at localhost

To simulate a build running on your own machine, open a tunnel with ish connect, then point the study at the tunnel URL or use platform="code". Before dispatching, Claude Code can call connect_status to confirm the tunnel is registered, so a missing tunnel fails fast instead of stalling inside the cloud browser.

​
Where to go next

Every MCP tool

All 42 hosted tools, grouped by domain, each with its annotation tier.

MCP resources

The ish:// resources for identity, docs, screenshots, and media.

Runs and asks

When to run a study and when to fire a lightweight ask.

Other clients

Wire Cursor, VS Code, ChatGPT, and the rest to the same server.