Skip to main content
FetchSandbox

FetchSandbox MCP

Connect FetchSandbox to your builder

Choose n8n, Codex, Claude Code, Cursor, Lovable, Replit or Bolt. Then follow four steps: add your account key, configure remote MCP, test the connection and validate your actual app.

Choose your builder

Account key

Add your key in your builder's settings or environment. Never paste it into chat. Isolated twins don't need live vendor keys.

Get account key

Test the connection, then validate your app

The first prompt makes a real read-only list_workflows call for spec_slug stripe. A working connection doesn't verify your code or redirect your app's provider calls. The second prompt uses validate_integration to agree on expected behavior, point provider calls at isolated twins and invoke your running app. Local apps use a managed tunnel. Hosted workflows use a protected, reachable trigger.

Remote MCP configuration
https://fetchsandbox.com/mcp/v1
Confirm an actual tool call
Call FetchSandbox list_workflows with spec_slug stripe and tell me the actual result.
Verify your running app and inspect a receipt
Use FetchSandbox validate_integration for this running app. Agree the observable expected behavior with me, configure the isolated twins, invoke the actual app and report the receipt, including anything failed or unmeasured. Keep polling the same get_job until it reaches a terminal state.

Related receipts

All workflows →

Historical runs recorded against isolated twins. You can inspect each receipt and its evidence. Not a new execution or production certification.

Lead recovery in n8n Cloud
hubspotgmailgoogle-calendarslack

Lead recovery in n8n Cloud

Passed

n8n Cloud lead flow from HubSpot to Gmail to Calendar to Slack. The run rehearsed retries, uncertain results and a restart of our worker. It doesn't cover an n8n host crash or live delivery.

25Passed0Failed0Not measured
Evidence details

Each receipt is one individual dated run against isolated provider twins, not live vendors. The caller declared the app revision, and it is not attested. Workflow docs are pinned to the commit shown here. A status appears only when the original verdict, counts, completeness and app_verified all support it, and counts are never merged. Some source exports, including the n8n lead flow, are not public. These public examples are separate from proving your own app through your builder, and they don't show that each native client was tested.

{"verdict":"verified","complete":true,"applicationVerified":true,"appVersion":{"value":"n8n-export-74f53408d9f76f9ccb3787bb33996c1d962321d06c3f62a0117810bc0cbd5590-bridge-0b39db8027ef","source":"declared"},"sourceRevision":null}
Pawsome Pantry checkout in Lovable
paddleresend

Pawsome Pantry checkout in Lovable

Partial

Pawsome Pantry on Lovable, with Paddle checkout and Resend email. Two paths stayed unmeasured, so this isn't full acceptance.

6Passed0Failed2Not measured
Evidence details

Each receipt is one individual dated run against isolated provider twins, not live vendors. The caller declared the app revision, and it is not attested. Workflow docs are pinned to the commit shown here. A status appears only when the original verdict, counts, completeness and app_verified all support it, and counts are never merged. Some source exports, including the n8n lead flow, are not public. These public examples are separate from proving your own app through your builder, and they don't show that each native client was tested.

{"verdict":"inconclusive","complete":false,"applicationVerified":false,"appVersion":{"value":"pawsome-pantry-v1.1","source":"declared"},"sourceRevision":null}