Troubleshooting

Health Check

Before troubleshooting specific issues, verify that the MCP server is running:

curl http://162.55.224.224:3002/health

A successful response means the server is online and accepting connections. If this fails, the server may be down or unreachable from your network.

Connection Issues

Server Not Responding

Symptoms: Your AI client shows "connection failed" or "server unreachable."

Possible causes:

• The hosted server may be temporarily down
• Your network may block the connection (firewall, VPN, proxy)
• The server URL is incorrect

Solutions:

1. Run the health check above to verify server status
2. Check your firewall settings — the server runs on port 3002
3. Verify the URL in your configuration matches http://162.55.224.224:3002/mcp
4. If using a VPN, try connecting without it

MCP Tools Not Appearing

Symptoms: Your AI assistant does not offer Qamera AI tools.

Solutions:

• Cursor: Restart Cursor after saving .cursor/mcp.json
• Claude Desktop: Restart the application after updating the config
• Verify your configuration JSON is valid (no trailing commas, correct structure)
• Check that the MCP server entry is under the mcpServers key

Authentication Errors

Invalid API Key

Symptoms: Requests fail with an authentication or "unauthorized" error.

Solutions:

1. Verify your API key is correct — copy it again from your Qamera AI account settings
2. Check the header format:
   • Cursor SSE: "Authorization": "Bearer YOUR_KEY" (include "Bearer " prefix)
   • Alternative: "X-Api-Key": "YOUR_KEY" (no prefix needed)
3. Make sure there are no extra spaces or newline characters in the key
4. Generate a new key if the current one may have been revoked

Expired API Key

Symptoms: Previously working connection suddenly returns authentication errors.

Solutions:

1. Log in to Qamera AI and check your API key status
2. Generate a new API key if needed
3. Update the key in your MCP client configuration
4. Restart your AI client

Rate Limiting

Symptoms: Requests fail intermittently with rate limit errors, especially during batch operations.

Solutions:

1. Reduce the frequency of requests — add pauses between batch operations
2. Avoid running multiple MCP sessions with the same API key simultaneously
3. If you need higher limits, contact the Qamera AI team

Insufficient Credits

Symptoms: Content generation requests fail with a credits-related error.

Solutions:

1. Check your credit balance in the Qamera AI dashboard under Credits
2. Purchase additional credits or upgrade your subscription plan
3. Read-only operations (listing products, viewing packshots) do not consume credits

Local Server Issues

If you are running the MCP server locally:

Build Errors

cd mcp-server-for-shorts-lab
npm install
npm run build

Make sure you have Node.js installed (version 18 or higher).

Environment Configuration

Create a .env file in the server directory:

QAMERA_AI_API_BASE_URL=https://qamera.ai
PORT=3002

Port Already in Use

If port 3002 is occupied, change it in your .env file and update your client configuration to match.

Still Need Help?

• Check the MCP server repository for the latest documentation
• Open an issue on the repository for server-specific problems
• Contact the Qamera AI support team for account or platform issues