---
title: "Troubleshooting"
description: "Common Norcaster issues and fixes for deployments, provider-backed models, MCP input, workflow payloads, redaction, and portal builds."
canonical: https://www.norcaster.com/docs/troubleshooting
---
<!-- Generated at build time from the rendered page by portal/scripts/generate-llms.mjs. The page is the source of truth; edit it, not this file. -->

Troubleshooting

# Common issues and fixes

Use this page when a deployment, provider integration, MCP workflow, redaction chain, or portal build does not behave as expected.

## Deployment stays in Provisioning

**Likely cause:** Provider-backed deployments should become ready once the inference target is bound. If they do not, the binding or API rollout may be stale.

**Fix:** Open the deployment detail, confirm it has an inference target, then restart or redeploy the API if provider readiness backfill has not run.

## Model node has no content to send

**Likely cause:** The model node prompt\_field points at a payload field that does not exist.

**Fix:** Use a field that exists after upstream nodes. If redact\_text edits raw\_tickets.text in place, use prompt\_field: raw\_tickets.text. If you create a top-level redacted\_text field, use prompt\_field: redacted\_text.

## Claude or another provider does not receive MCP data

**Likely cause:** The mcp\_input result\_field or model prompt\_field is mismatched, or the MCP tool returned only structured data without text.

**Fix:** Check that mcp\_input writes a stable result\_field and that the model reads <result\_field>.text. Norcaster normalizes MCP output into text, raw, items\_count, and has\_text.

## Customer names or phone numbers appear in model output

**Likely cause:** The redaction patterns did not match the content, or the model read raw context before redaction.

**Fix:** Run redact\_text before model, add extra\_patterns for international phone formats, and inspect What reached Claude in the audit log.

## Portal dev server fails with EADDRINUSE on port 3001

**Likely cause:** Another Next.js dev server is already listening on port 3001.

**Fix:** Stop the old process or run pnpm dev -- -p 3002.

## What to collect before asking for help

- The workflow ID, deployment ID, and execution ID.
- The node that failed and the exact error message.
- The relevant node config, especially `result_field`, `fields`, and `prompt_field`.
- The audit log section showing what reached the provider model.