What does it mean to connect an app to Claude Code?

You wire an integration node into the agent's tools handle. Each operation that app exposes becomes a tool Claude Code can call directly, so it can take real actions in that app instead of only describing them.

Do I need to write any code to set this up?

No. You pick the integrations, click to open the agent in NoClick, connect your accounts, and the tools are ready. There is no glue code to maintain.

Does Claude Code run on my own machine?

No. NoClick runs the harness for you in a hosted sandbox, so there is nothing to install and the agent can run on a schedule or from a trigger.

Can Claude Code use more than one app in a single run?

Yes. Wire as many integrations into the same agent as you need and it can use all of them together while completing a task.

Claude Code

Connect Claude Code to LegalMatch

Run Claude Code as a hosted agent in NoClick with LegalMatch wired into its tools handle. It can use LegalMatch directly while it works. No glue code, nothing to install. Click below to open a ready-to-run agent and connect your account.

Loading preview…

Opens a workflow with 21 tools ready to use.

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own Claude Code, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in LegalMatch
A preset of real LegalMatch operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect LegalMatch
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Claude Code first calls in. Claude Code connects when a session starts — run claude, or restart a running one.
Run this in your terminal
$claude mcp add --transport http noclick https://mcp.noclick.app/s/<your-link>
<your-link> is your personal server URL — setup mints it for you.

Tools Claude Code gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

LegalMatch

21 tools

Run Full Sync

Trigger Full Pipeline: Trigger the full sync pipeline (backfill → mapping → banner → reconcile → gap detection).

Run Banner Sync

Trigger Banner Sync: Manually trigger banner sync.

Run Backfills

Trigger All Backfills: Manually trigger all 4 backfill entity types sequentially.

Run Mapping Sync

Trigger Mapping Sync: Manually trigger mapping sync.

Run Reconciliation

Trigger Reconciliation: Manually trigger reconciliation.

Run Gap Detection

Trigger Gap Detection: Manually trigger gap detection.

Get Mapping Suggestions

Get Suggestions: Get suggested SF account matches for a QBO customer.

Get Sync Status

Admin Sync Status: JSON endpoint polled by dashboard for real-time sync card updates.

Get Gap Summary

Admin Gap Summary: JSON endpoint for gap summary — polled by dashboard after gap detection.

Get Learning Insights

Admin Learning Data: JSON API: all learning insights for programmatic access.

List Logs

Admin Logs Raw: Parsed log entries as JSON array (for programmatic access).

Assign Mapping

Admin Assign Mapping: Form handler: manually assign a QBO customer to an SF account.

Mark Paid

Admin Mark Paid: Set grace_period_cleared = 1 for an attorney's qb_record — hides the payment banner.

Unmark Paid

Admin Unmark Paid: Clear grace_period_cleared back to 0 — re-shows the payment banner.

Resolve Gap

Admin Resolve Gap: Resolve a single gap: dismissed, false_alarm, or fixed.

Resolve All Gaps

Admin Resolve All Gaps: Batch-resolve all open gaps of a specific type.

Get Banner Audit Status

Admin Banner Audit Status: Current job state, for the page to poll. Cheap and read-only.

Get Banner Audit

Admin Banner Audit Json: JSON API for banner audit — for programmatic/scheduled checks.

Adjust Mapping Confidence

Admin Adjust Confidence: Trigger L1 confidence adjustment: apply learned feedback to mapping confidence scores.

Acknowledge Review

Admin Acknowledge Review: Accept a finding as reviewed-and-correct.

Revoke Review

Admin Revoke Review: Withdraw a verdict, bringing the finding back to the live list.

About Claude Code

Claude Code is Anthropic's command-line coding agent. In NoClick you run it as a hosted agent and connect your real apps to its tools handle, so it does far more than write code. Wire in an integration and Claude Code can read and act on Slack, Linear, your database, and more on its own, calling each one as a tool while it works. It is the same capable agent, pointed at your actual workflows instead of a sandbox.

Careful multi-step planning before it acts

Reliable on long, structured tasks

Reads context thoroughly before making changes

Comfortable across code, data, and APIs