Last updated:
MCP
MCP lets you create and manage your own Model Context Protocol (MCP) configurations. Each configuration exposes an MCP server that external MCP clients, most commonly AI providers such as OpenAI, can connect to.
This is the reverse direction of the external MCP tools an agent can use: here, Any2Info is the one exposing capabilities, not consuming them.
Each MCP configuration exposes selected dataflows and dataclips as capabilities on the generated MCP server.
Designer overview
Section titled “Designer overview”The MCP designer has three main areas.
Configuration explorer
Section titled “Configuration explorer”On the left side of the designer, you can create, edit, delete, and organize MCP configurations into folders.
Configuration editor
Section titled “Configuration editor”The center section contains the editor for the selected configuration, with two tabs:
General shows the configuration name and the generated endpoint URL. The endpoint is automatically generated based on the configuration’s GUID, and can be copied for use by MCP clients.
Capabilities lists all configured capabilities in a table:
| Property | Description |
|---|---|
| Name | Name of the dataflow or dataclip. |
| Type | Source type (dataflow or dataclip). |
| Description | Description exposed for the capability. |
| Active | Whether the capability is available to MCP clients. |
Add a capability with the Add capability button above the table; remove one from its row’s ellipsis menu. Capability ordering is managed internally and can’t be changed manually. A dataflow and a dataclip may share the same name, since they’re distinguished by their capability type.
The description for a capability can be maintained either within the individual dataflow or dataclip designer, or directly from the capability row using the ellipsis menu.
Properties
Section titled “Properties”The right-hand panel holds the high-level configuration settings:
| Property | Description |
|---|---|
| Explanatory note | Optional note describing the purpose of the configuration. |
| Disabled | Disables the entire configuration. |
Internal identifiers such as the GUID and static ID are shown for reference, but aren’t meant to be modified.
Authentication
Section titled “Authentication”The generated MCP endpoint is secured using the standard Any2Info authentication mechanism: OAuth 2.0 with an Any2Info bearer token. Clients must authenticate successfully before accessing the MCP server.
Capabilities
Section titled “Capabilities”Capabilities define which Any2Info resources are exposed through the MCP server. Currently supported types are dataflows and dataclips.
If a referenced dataflow or dataclip is deleted after being added to a configuration, it’s automatically ignored when an MCP client retrieves the available capabilities, so invalid capabilities are never exposed.
- Create a new MCP configuration.
- Set the explanatory note and enabled/disabled state.
- Open the Capabilities tab and 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
Section titled “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 a capability using the Active flag instead of removing it.
- Disable an entire configuration when it should no longer be accessible.
- Organize configurations into folders to simplify management.