Generic MCP
Connect a custom or third-party MCP server to Konrado.AI
Use Generic MCP when you already have an MCP-compatible server or a third-party data source exposed through an MCP endpoint.
What Is It?
Generic MCP connects Konrado.AI to a custom Model Context Protocol endpoint. Use it when your support team needs data from an internal system, private API, inventory database, provisioning layer, or third-party tool that is not covered by a dedicated integration.
What It Can Do
| Capability | How it helps support |
|---|---|
| Discover MCP tools/resources | Let Konrado.AI understand what your custom server exposes |
| Query custom systems | Add support context from internal APIs or third-party systems |
| Normalize niche workflows | Give AI replies access to business-specific facts that are not in WHMCS, SupportPal, or panels |
| Extend over time | Add new MCP tools as your support needs grow |
What It Cannot Do
| Not supported by default | Why this matters |
|---|---|
| Guarantee read-only behavior | Your MCP server controls what actions are available |
| Reach private networks by itself | Use Remote Agent when the MCP endpoint is not publicly reachable |
| Infer unsupported data | The AI can only use tools/resources exposed by your MCP endpoint |
| Replace endpoint-level auth and audit controls | You still need proper token, logging, and permission design |
Security Model
Treat the MCP API key as a secret and expose the minimum set of tools required for support. If the MCP server can mutate data, explicitly document those actions and consider a read-only proxy for Konrado.AI.
Ticket Examples
- "Can you check the provisioning state in our internal platform?"
- "Does this customer have the custom add-on enabled?"
- "What does our inventory system say about this service?"
- "Can you fetch the latest status from our private API?"
- "Why does this customer record differ from WHMCS?"
Prerequisites
- Access to Konrado.AI Integrations.
- A reachable MCP server URL, for example
https://yourdomain.com/mcp. - An API key or token accepted by the MCP server.
- A short integration name that helps your team identify the connection.
MCP-Compatible
MCP means Model Context Protocol. An MCP-compatible server exposes a standard endpoint that lets Konrado.AI discover and call tools or read resources through the MCP protocol.
If your data source is a regular internal API, place an MCP server in front of it, then connect that MCP endpoint here.
Installation
In Konrado.AI, open Integrations > Applications, click Add Integration, and choose Generic MCP.
Fill in the form:
| Field | What to enter |
|---|---|
| Integration Name | A label for this connection, for example EU Node |
| Server URL | The MCP endpoint URL, for example https://yourdomain.com/mcp |
| API Key | The token sent to your MCP server |
The API key is sent as a bearer-style authentication token unless your MCP endpoint documents a custom header format. If your endpoint expects Basic auth or a custom header, configure the MCP server to accept Konrado.AI's token format or place a small proxy in front of it.
Click Test Connection. If the test passes, click Save.
Verify Success / Failure
A successful test confirms that Konrado.AI can reach the MCP endpoint, authenticate, and discover the expected MCP capabilities.
Troubleshooting
| Issue | What to check |
|---|---|
| Test Connection fails | Confirm the Server URL is reachable from Konrado.AI and points to the MCP endpoint |
| Authentication fails | Confirm the API Key matches the token expected by the MCP server |
| Data is missing | Verify the MCP server exposes the expected tools or resources |
| Private target is not reachable | Use Remote Agent when the MCP server is not publicly reachable |
| Unexpected actions are available | Restrict tools in your MCP server or place a read-only proxy in front of it |
Remove
Delete the Generic MCP integration in Konrado.AI and revoke the token on your MCP server.