Skip to main content
Isometric provides access to a remote MCP server. It allows suppliers, partners and verifiers to add key context on Isometric’s protocols, the Standard and the Certify and Registry platform into common AI chat or coding assistants.

Available tools

Isometric’s MCP server enables AI assistants to access the following resources to provide context to their responses:
  1. The Isometric Standard
  2. Isometric’s protocols
  3. Isometric’s protocol modules
  4. User guides for the Certify and Registry platform documented on this site
  5. Isometric’s API documentation

Connecting to the server

The Isometric MCP server is provided at:
If you are using the sandbox environment, a version connected to its data is available at:
You need to have a user account on the Certify or Registry platform to connect to it. Once connected, you can review which clients you have authorized, see when they were last used, and revoke their access under Team settings → AI Integrations.

Supported clients

Pre-approved clients

Remote MCP server integration is supported by most modern AI assistants. The clients below support MCP server connections and have been pre-approved by Isometric for authentication. Setup instructions are available from the link on each provider.

Using the connector with other clients

You may also be able to use the Isometric MCP server with other clients. In order to connect, the following features must be supported by the client: The domains for the URI to which users are redirected after authorizing and for the CIMD client ID (if present) must also be allowlisted by Isometric. If connecting to the server fails with a Failed to fetch CIMD document or Failed to verify TLS certificate of CIMD/redirect URI error, but your client works correctly with other MCP servers, please contact Isometric at support@isometric.com to request domain approval.
If your client prefers the DCR method and fails because it does not discover support for it, you may need to configure a client ID, as with the preregistration method above. For example, Google Gemini CLI requires this approach as of May 2026.

Setup examples

Claude

Isometric is available as an official Claude connector.
1

Open connector settings

Open Settings → Customize → Connectors on Claude.ai or in Claude Desktop.
2

Browse connectors

Click Add → Browse connectors and find Isometric in the connector directory.
3

Connect to the Isometric connector

Click Connect. If you are not already logged into Isometric in your browser, you will be prompted to log in first. You will then be shown a consent screen to allow the MCP connection. Click Allow to complete the connection.
If you are on a Claude Team or Enterprise plan, the connector may first need to be enabled for your organization. Organization owners can manage connectors at Organization settings → Connectors.
The official connector uses the production server. To connect to the sandbox environment instead, add its URL as a custom connector via Add → Add custom connector on the same settings page.
Claude Desktop showing the Isometric MCP connectorClaude Desktop showing the response to a question about API usage

Example responses from Claude Desktop with the Isometric MCP connector

ChatGPT

Setup instructions are also available in the OpenAI ChatGPT MCP documentation.
1

Add MCP server

Go to the Settings → Plugins → MCPs tab. Add MCP server with type as Streamable HTTP and URL as https://api.isometric.com/mcp or https://api.sandbox.isometric.com/mcp as required.
2

Add client_id to configuration

In ~/.codex/configuration.toml, add oauth = { client_id = "chat-gpt" } under the section corresponding to the MCP server you just added. E.g.

Suggested prompts

Some suggested prompts to test the MCP server connection are shown below:

Usage tips

General advice

If you are unfamiliar with AI assistants, reading educational guides on working with these tools, such as Anthropic’s free AI Fluency course are a good starting point. Assistants can also help guide you on how to get the most out of them: asking them how to work with them effectively as an initial prompt can be a helpful place to begin. If asking multiple different questions, it’s generally best to start a new chat for each question rather than continuing a previous chat, as models usually perform better with shorter conversation histories. If you want to clarify a prompt to get a better answer, editing your original prompt is usually more effective than adding further context in a second prompt.

Base prompts

Using a base prompt can help to ensure more reliable behavior from an AI assistant. For chats using the Isometric MCP server, consider using the following base prompt or a similar version: