genetic-orange•6d ago

getting error when connecting MCP tool?

{ "id": "log-155", "level": 50, "time": 1755993059136, "timestamp": 1755993059136000000, "severityText": "ERROR", "severityNumber": 17, "body": "MCP tool call failed", "attributes": { "category": "tool", "callId": "8a15ff37-d0d0-4a75-ac86-c71bd0bb5aaf", "orgId": "177d5905-5175-47fd-bc67-4e8d47b9ca38", "error": "Failed to connect to MCP server" } } This is the respones I found in the logs when trying to connect to my MCP endpoint using Streamable HTTP. I'm trying to decipher if by "failed to connect" they mean that there was some auth issue / issue when trying to use one of the endpoints on that server or if it just failed to even connect at all altogether. my server is running on port 3005 and has an endpoint for shttp at 3005/mcp, but I tried both and still got the error. No logs in my ec2 where it's hosted either which make me wonder if it even connected at all. Anybody encounter this and know the correct setup or fix?

2 Replies

Shubham Bajaj•6d ago

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards,
Vapi
Customer Support Team

Shubham Bajaj•3d ago

Hi bobatitan99, To troubleshoot connectivity issues with the MCP tool, please ensure the following steps: 1. Validate API Key: Confirm that your Vapi API key is correct and included in the MCP server configuration as a bearer token. This key should be retrieved from the Vapi dashboard. 2. Check Configuration: Make sure your MCP server configuration is following the format below:

   {
     "mcpServers": {
       "vapi-mcp": {
         "command": "npx",
         "args": [
           "mcp-remote",
           "https://mcp.vapi.ai/mcp",
           "--header",
           "Authorization: Bearer ${VAPI_TOKEN}"
         ],
         "env": {
           "VAPI_TOKEN": "YOUR_VAPI_API_KEY"
         }
       }
     }
   }

   {
     "mcpServers": {
       "vapi-mcp": {
         "command": "npx",
         "args": [
           "mcp-remote",
           "https://mcp.vapi.ai/mcp",
           "--header",
           "Authorization: Bearer ${VAPI_TOKEN}"
         ],
         "env": {
           "VAPI_TOKEN": "YOUR_VAPI_API_KEY"
         }
       }
     }
   }

Replace YOUR_VAPI_API_KEY with your actual API key. 3. Server URL: Ensure your MCP server URL (https://mcp.vapi.ai/mcp) is correct and accessible from your network environment. 4. Network Access: Verify that there are no firewall or network restrictions blocking access to the https://mcp.vapi.ai/mcp endpoint. 5. Protocol and Headers: If you are using custom headers or a specific protocol, ensure they are correctly configured in your tool settings. Refer to the Model Context Protocol (MCP) Integration documentation for additional details on setup and configuration. If the problem persists after these checks, more detailed logs or error messages might be necessary to diagnose further.

Model Context Protocol (MCP) Integration | Vapi

Connect your assistant to dynamic tools through MCP servers for enhanced capabilities.

getting error when connecting MCP tool?

Did you find this page helpful?