FutureAGI MCP: evals and simulations next to your code

Set up FutureAGI in Claude, ChatGPT or Cursor

1. 1Click Connect FutureAGI free and sign in with your FutureAGI account.
2. 2The list appears once you connect. Lookups of datasets, evals and scenarios are safe to keep; switch off anything that runs tests or changes your FutureAGI setup if you'd rather do that yourself.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app which eval tasks exist for your support agent's project, then open Activity to see the call.

Agent evaluation work in Claude Code or Cursor

• List eval tasks and custom eval configs for a project.
• Browse datasets, annotation queues and annotation labels.
• Find simulation scenarios and personas for an agent definition.
• Review configured run tests without executing them.

Visibility into FutureAGI calls

• Switch off any FutureAGI tool your team doesn't need; it's hidden and refused if called.
• Policies check every call, so an API key pasted from your agent's config can be blocked before it's sent.
• Activity records every call your AI apps make to FutureAGI.

What you get with FutureAGI and ContextGate

• Your AI apps can use FutureAGIClaude, Cursor, ChatGPT and other AI apps reach FutureAGI through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any FutureAGI tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

FutureAGI tools

Examples of what your AI apps can do in FutureAGI. You'll see the exact list of tools after you connect it.

• List Agent DefinitionsList one page of agent definitions in the connected FutureAGI organization, optionally filtering by type, name, assistant ID, or agent ID. Returns next_cursor to continue.
• List Annotation LabelsList one page of FutureAGI annotation labels by type, name, project, or dataset, optionally including usage counts. Returns next_cursor to continue.
• List Annotation QueuesList one page of FutureAGI annotation queues by status or name, optionally including item counts. Returns next_cursor to continue.
• List Custom Eval ConfigsList custom evaluation configurations, optionally restricted to a FutureAGI project or evaluation task.
• List DatasetsList one page of datasets in the connected FutureAGI organization, optionally searching by name. Returns next_cursor to continue.
• List Eval TasksList one page of FutureAGI evaluation tasks, optionally filtering by project ID or task name. Returns next_cursor to continue.
• List PersonasList one page of built-in and workspace personas for FutureAGI simulations, with type, simulation-mode, and text filters. Returns next_cursor to continue.
• List Run TestsList one page of configured FutureAGI run tests without executing them, optionally filtering by name, source type, or prompt template. Returns next_cursor to continue.
• List ScenariosList one page of FutureAGI simulation scenarios, optionally filtering by agent definition, agent type, or search text. Returns next_cursor to continue.