> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/user-guide/data-sources/mcp/test-an-mcp-tool.md).

# Test an MCP tool

Test a connected tool with known inputs before using its output in an app, workflow, or agent.

## Before you start

[Connect an MCP server](/user-guide/data-sources/mcp/connect-an-mcp-server.md). Check the actions exposed by that server and the required parameters. Names and available operations depend on the server.

## Test the tool

1. Open the connected MCP resource and select an available action.
2. Review the action description and required inputs.
3. Enter a simple test value. For a weather action, this might be a city such as `Berlin`.
4. Run the action and inspect its response.
5. Repeat with another input to confirm the output changes as expected.

## Verify

Check that the response refers to the requested input and includes the fields your app needs. Check units and dates for weather data. A successful connection alone does not establish that every action is authorized.

## Troubleshooting

Missing actions can indicate the wrong server URL or limited authorization. Failed actions can result from missing inputs, expired credentials, rate limits, or a server error.

See the [weather example](/user-guide/data-sources/mcp/using-mcp-server-tools-in-jetadmin-with-weather-mcp-via-smithery.md) and [MCP limitations](/user-guide/data-sources/mcp/limitations-and-troubleshooting.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.jetadmin.io/user-guide/data-sources/mcp/test-an-mcp-tool.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.