> 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/use-mcp-tools-in-agents-and-workflows.md).

# Use MCP tools in agents and workflows

Use a connected MCP action after confirming it works with a manual test.

## Before you start

Connect the server and test the action with known inputs. Note its required parameters, response fields, and whether it changes external data.

## In a workflow

1. Select an action from the connected MCP resource.
2. Supply its required inputs from the workflow's available values.
3. Run a test and inspect the action output.
4. Use the returned fields in the following step.

For workflow setup, follow [Workflow overview](https://docs.jetadmin.io/workflow/overview).

## In an agent

Make the connected resource's tools available in the agent's configuration. Describe when the agent should use the tool and what information it needs from the user. Test a specific request, then inspect the tool inputs and returned result.

For example, ask a weather agent for a forecast for a named city and date. Verify that it used those values rather than substituting a different location.

## Verify

Check the tool call as well as the final answer. Confirm that downstream steps use the intended response fields.

To connect an existing Jet Admin agent to an external MCP client, follow [Using Agents with MCP Clients](/ai-agents/slack-telegram-email-and-mcp/using-agents-with-mcp-clients.md). That is a different setup from adding an external MCP server as a resource.


---

# 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/use-mcp-tools-in-agents-and-workflows.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.