MCP Server

AI assistants can access data stored in TQ Data Foundation via a Model Context Protocol (MCP) server. This allows users to query and explore asset collections using natural language through AI tools such as Claude Code, Claude Desktop, OpenAI Codex and VS Code with GitHub Copilot.

The MCP server is a remote server, reached over HTTPS. Users sign in with their existing Data Foundation accounts and have access to the same asset collections they can already access in Data Foundation.

Important

The MCP server is a TQ Data Foundation feature that is enabled per environment by TopQuadrant. Individual tools have different maturity levels: the read and query tools are generally available (GA), while the write and UI-interaction tools are in beta and are only exposed when beta tools are enabled for your environment. See Tool Maturity below. Behavior, tool names, and availability may change, and the beta tools carry no availability or support guarantee.

Features

The MCP server allows AI assistants to:

  • List available asset collections in TQ Data Foundation

  • Run read-only SPARQL queries against TQ Data Foundation

  • Read the state of the Data Foundation UI in your browser, such as the currently selected asset and any constraint violations reported for it

  • Suggest fixes for constraint violations, to be applied from the Problems and Suggestions display on the Form Panel, see Enable Chat Prompt Buttons

Example questions you can ask your AI assistant:

  • “List asset collections in TQ Data Foundation”

  • “How many triples are in the Geo taxonomy in Data Foundation?”

  • “List people in the Kennedys graph in Data Foundation”

  • “Count the number of instances for each class in the Northwind collection in Data Foundation”

  • “In TQ create suggestions” (asked automatically when you use the Enable Chat Prompt Buttons button on a constraint violation)

Tool Maturity

The MCP server exposes its capabilities as individual tools. Tools fall into two maturity levels:

  • Generally available (GA) tools are read-only query and discovery tools. They are always available when the MCP server is enabled for your environment.

  • Beta tools are still being finalized. They are only exposed when beta tools have been enabled for your environment by TopQuadrant, and their behavior, names, and availability may change before they reach GA. Most beta tools make changes (write to data or drive the Data Foundation UI); two are read-only but remain in beta because they are newer UI-integration capabilities.

Generally available (read / query) tools

Tool

Access

Description

list_asset_collections

Read

Lists all available asset collections in TQ Data Foundation and their named graph URIs.

sparql_query

Read

Runs a read-only SPARQL query against the TQ Data Foundation SPARQL endpoint.

Beta tools

Available only when beta tools are enabled for your environment.

Tool

Access

Description

sparql_update

Write

Executes a SPARQL Update operation against the Data Foundation SPARQL endpoint.

create_collection

Write

Creates a new asset collection in TQ Data Foundation and returns its assigned collection id.

add_suggestions

Write

Adds suggestions for fixing problems reported by the Form Panel for the currently selected asset (see Enable Chat Prompt Buttons).

set_selected_asset

Write (UI)

Selects an asset in the Data Foundation user interface.

set_script_panel_contents

Write (UI)

Inserts JavaScript code into the Script Editor panel of the Data Foundation user interface.

set_sparql_panel_contents

Write (UI)

Inserts a SPARQL query into the SPARQL Query panel of the Data Foundation user interface.

set_turtle_source_contents

Write (UI)

Inserts Turtle source code into the Source Code panel of the Data Foundation user interface, selecting a specific asset first.

get_ui_state

Read (UI)

Returns the current state of the Data Foundation user interface as seen in the user’s browser. Read-only, but in beta.

run_ads_script

Read

Executes a read-only JavaScript expression in the TopBraid ADS scripting engine. Read-only, but in beta.

Onboarding

Note

This feature must be enabled by TopQuadrant before it can be used.

The MCP server must be enabled by TopQuadrant for a Data Foundation environment. Administrators should contact TopQuadrant Support to have the MCP server enabled.

Server URL

Once the MCP server has been enabled for your environment, you receive its URL and can connect your AI application. For a Data Foundation instance reached at https://{hostname}/edg, the MCP server URL is typically https://mcp.{hostname}/mcp. If you have not received your MCP server URL, contact your administrator or TopQuadrant Support.

Client Compatibility

The MCP server requires a client application that supports remote MCP over HTTPS with OAuth 2.1, PKCE, and Dynamic Client Registration (DCR).

Connecting an AI Application

The exact steps for adding a remote MCP server depend on the AI application. Refer to the application’s own documentation for the most up-to-date instructions, and use your MCP server URL. Brief pointers for several common applications follow.

Claude Code

Add the MCP server with the claude mcp add command, using the --transport http option and the server URL, for example:

claude mcp add --transport http data-foundation <your-MCP-server-URL>

Here data-foundation is a name you choose for the connection. See Connect to MCP servers (Claude Code).

Claude.ai, Claude Desktop and Claude Cowork

Remote MCP servers are added as custom connectors from the application’s settings. The exact steps depend on your Claude plan:

  • On Team and Enterprise plans, an organization owner adds the connector; members then turn it on for their own account.

  • On Max and Pro plans, add the connector directly from your own settings under Customize > Connectors.

See Get started with custom connectors using remote MCP.

OpenAI Codex

Add the MCP server with the codex mcp add command, specifying the server URL as a streamable HTTP server. See Codex MCP.

VS Code

Add the server through MCP: Add Server in the Command Palette, choosing the HTTP server type and entering the server URL. See Use MCP servers in VS Code.

Authorization

After you connect to the MCP server in your AI application, you are asked to authorize access to Data Foundation. An SSO authorization page opens in your browser. After you approve the request, the AI application is able to connect to Data Foundation on your behalf.

If the authorization page does not open automatically, check that your browser is not blocking pop-ups, or copy the authorization URL from the AI application and open it manually.

Once authorized, ask your AI assistant to list your asset collections in Data Foundation to confirm that the connection is working.