Skip to main content
Custom MCP Tools give you precise control over agent behavior by codifying specific actions into reusable, deterministic steps that execute exactly as defined—every time. You can create custom tools in a Connect AI workspace and then provide the endpoint to the workspace to your AI agent. For example, you can create an AI agent using Jira custom tools: the agent finds all unassigned high-priority Jira tickets and assigns them to the appropriate team members. You define the Jira custom tools in a workspace containing the Jira connection. You then provide the AI agent with the workspace endpoint containing the custom tools.

​
Prerequisites

  • Custom MCP tools are available to Growth+ and Connect AI Embed customers only.
  • Only Admin users can create and configure custom tools.
  • You must have created one or more workspaces. See Workspaces for more information on creating workspaces.

​
Custom Tool Types

You can add the following custom tool types to a workspace:
  • MCP System Tools–these are tools that apply to every asset in the workspace. These are data exploration and manipulation operations built into Connect AI. They expose operations such as getCatalogs and executeProcedure. System tools can only be enabled or disabled globally for a workspace, not individually.
  • Workspace Assets–these are tools that perform an action specific to your source data. You can configure actions such as get, search, and create for each workspace asset in order to optimize your query. For example, if your workspace includes the Jira Issues table, you can add tools to search for and create issues.
  • Custom SQL–you can create custom SQL tools for repeatable queries and operations. You can add optional or required parameters that are input to the SQL query.

​
Custom Tools Tab

The Custom Tools tab contains a list of the custom and system tools in the workspace.
Custom Tools Tab
The list contains the following information:
  • Tool Name—the user-defined tool name and its AI instructions.
  • Parameters—the number of parameters (required or optional) for the tool.
  • Enabled—the toggle switch to enable or disable the custom tool.
  • Edit (🖉)—edit the custom tool, including its name, instructions, or parameters.
  • Delete (🗙)—delete the selected tool. You can delete several custom tools at once by selecting the tools to delete and clicking the Delete button next to Custom Tools.

​
Add a Workspace Asset to a Workspace

To add a workspace asset:
1
From the main navigation, click Workspaces. The Workspaces page appears.
2
Select the workspace to create a custom tool in.
3
Click the Custom Tools tab.
Add a custom tool
4
Click Add. The Add Tool dialog appears.
5
Click Workspace Asset. The Add Asset dialog appears.
6
In Step 1, select the asset to configure as your custom tool. Click Next.
7
In Step 2, configure one or more actions to optimize your query. Select Actions to select every action. You can update these actions later.
8
Click Confirm to add the custom tools to the workspace. The tools appear in a disabled state.
List of custom tools
9
Click the edit icon to edit the tool.
10
In the tool’s edit screen, you can override the default values for the tool.
11
You can expand on the default AI instructions for the tool by setting boundaries and defining the intent of the tool. Here are some guidelines for writing effective AI instructions for a custom tool:
  • Be clear and specific about the tool’s purpose. Define what the tool does and what inputs it accepts.
  • Set clear boundaries. Explicitly state what the tool should and should not do.
  • Test your instructions against a wide variety of inputs.
12
Optionally, add parameters and/or edit the default parameters. By default, the parameters are required, but in certain cases you can select Optional to make a parameter optional.
13
When you are satisfied with the tool’s configuration, enable the tool.

​
Add a Custom SQL Tool to a Workspace

To add a custom SQL tool:
1
From the main navigation, click Workspaces. The Workspaces page appears.
2
Select the workspace to create a custom tool in. Click the Custom Tools tab.
Add a custom tool
3
Click Add. The Add Tool dialog appears.
4
Click Custom SQL. The custom SQL editor appears.
5
In the custom SQL editor, you can edit the tool name and add AI instructions. You can set boundaries for the type of data that can be returned.
6
Create a SQL statement. The documentation contains a complete SQL Reference for guidance.
7
Optionally, add parameters to the SQL statement. If you add parameters to the SQL statement, you must add the parameter name in the Parameters section of the tool’s definition.
Custom SQL tool
8
Click Validate SQL. You can also Open in Data Explorer to see the results of the SQL statement.
9
Click Save Changes to save the custom SQL tool.
10
The tool appears in your workspace. When you are satisfied with the tool’s configuration, enable the tool.

​
Add the Endpoint to Your Agent

Connect AI provides an endpoint to the custom tools in your workspace. In your workspace, click View Endpoints:
Custom tools endpoint
Copy the Remote MCP Server URL that appears in the AI (MCP) tab and paste it into your AI agent as a custom connector.