> For the complete documentation index, see [llms.txt](https://academy.any2info.com/any2info-academy/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/mcp.md). # 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: | Property | Description | | ----------- | -------------------------------------------------------------- | | 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. | Property | Description | | ---------------- | -------------------------------------------------------------- | | 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 | Setting | Required | Description | | ---------------- | -------- | ---------------------------------------------------- | | 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: | Type | Description | | -------- | ---------------------------------------- | | 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: 1. Create a new MCP configuration. 2. Configure the explanatory note and enabled/disabled state. 3. Open the **Capabilities** tab. 4. Select **Add capability**. 5. Add one or more Dataflows or Dataclips. 6. Verify the generated endpoint URL. 7. 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 | Version | Date | Change | | ------- | ------------- | ------------------------------------ | | 1.0 | June 30, 2026 | Initial documentation version added. | --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.