MCP
Category: AI Studio
Version: 1.0
Last updated: June 30, 2026
Author: Any2Info
Description
The MCP module allows users to create and manage Model Context Protocol (MCP) configurations within the Any2Info software suite.
Each configuration exposes an MCP service that can be accessed by external MCP clients, most commonly AI providers such as OpenAI. An MCP configuration defines which resources are available to connected clients by exposing capabilities.
In the initial version, two capability types are supported:
Dataflows
Dataclips
Each selected Dataflow or Dataclip becomes an available capability on the generated MCP server.
The module can be accessed through:
AI Studio → MCP
Designer Overview
The MCP designer consists of three main areas.
Configuration Explorer
Located on the left side of the designer.
This panel allows users to:
Create new MCP configurations
Edit existing configurations
Delete configurations
Organize configurations into folders
Configuration Editor
The center section contains the editor for the selected MCP configuration.
The editor currently contains two tabs:
General
Displays general information about the configuration, including:
Configuration name
Generated endpoint URL
The endpoint URL is automatically generated based on the configuration GUID and can be copied for use by MCP clients.
Capabilities
Displays all configured MCP capabilities in a table.
Each capability contains:
Name
Name of the Dataflow or Dataclip.
Type
Source type (Dataflow or Dataclip).
Description
Description exposed for the capability.
Active
Determines whether the capability is available to MCP clients.
Capabilities can be added using the Add capability button above the table.
Available capability types are:
Dataflow
Dataclip
Capabilities can be removed using the row ellipsis menu.
Capability ordering is managed internally and cannot be changed manually.
The description for a capability can be maintained in two ways:
Within the individual Dataflow or Dataclip designer
Directly from the capability row using the ellipsis menu
The Active state allows administrators to temporarily disable individual capabilities without removing them from the configuration.
Note
A Dataflow and a Dataclip may have the same name because they are distinguished by their capability type.
Properties
The right-hand properties panel contains the high-level configuration settings.
Explanatory Note
Optional note describing the purpose of the MCP configuration.
Disabled
Disables the entire MCP configuration.
Internal identifiers such as the GUID and static ID are displayed for reference but are not intended to be modified.
Configuration Options
Explanatory Note
No
Optional description for administrators.
Disabled
No
Determines whether the MCP configuration is enabled.
Authentication
The generated MCP endpoint is secured using the standard Any2Info authentication mechanism.
Authentication uses:
OAuth 2.0
Any2Info Bearer Token
Clients must authenticate successfully before accessing the MCP server.
Endpoint
Each MCP configuration exposes a unique endpoint.
Characteristics:
Automatically generated
Based on the configuration GUID
Read-only
Can be copied directly from the General tab
Capabilities
Capabilities define which Any2Info resources are exposed through the MCP server.
Currently supported capability types are:
Dataflow
Exposes a Dataflow as an MCP capability.
Dataclip
Exposes a Dataclip as an MCP capability.
If a referenced Dataflow or Dataclip is deleted after being added to the configuration, it is automatically ignored when an MCP client retrieves the available capabilities.
This prevents invalid capabilities from being exposed while preserving the configuration.
Usage
Typical workflow:
Create a new MCP configuration.
Configure the explanatory note and enabled/disabled state.
Open the Capabilities tab.
Select Add capability.
Add one or more Dataflows or Dataclips.
Verify the generated endpoint URL.
Configure an external MCP client (for example OpenAI) to connect to the endpoint using an Any2Info OAuth Bearer Token.
Tips & Best Practices
Only expose Dataflows and Dataclips that are intended for external AI consumption.
Use meaningful descriptions to improve the discoverability of capabilities by AI clients.
Temporarily disable capabilities using the Active flag instead of removing them.
Disable an entire MCP configuration when it should no longer be accessible.
Organize configurations into folders to simplify management.
Notes
Capability names are inherited from the associated Dataflow or Dataclip.
A Dataflow and Dataclip may share the same name because their capability types differ.
Capability ordering is managed automatically.
Deleted source objects are automatically filtered from the exposed MCP capabilities.
Changelog
1.0
June 30, 2026
Initial documentation version added.
Last updated
Was this helpful?