# FutureAGI — how to use (mcp.ai)

Connect your FutureAGI account and use 9 tools for artificial intelligence straight from your AI agent. Connect with your own API key. FutureAGI provides evaluation, observability, simulation, dataset, and annotation APIs for building and improving AI systems.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_futureagi?ms=1787291460000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `futureagi_list_agent_definitions`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/futureagi`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/futureagi/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/futureagi/list/agent/definitions` — List 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.
  - body: { limit?: integer, search?: string, agent_type?: string, next_cursor?: string, agent_definition_id?: string }
- `POST https://api.mcp.ai/api/futureagi/list/annotation/labels` — List one page of FutureAGI annotation labels by type, name, project, or dataset, optionally including usage counts. Returns next_cursor to continue.
  - body: { type?: string, limit?: integer, search?: string, dataset?: string, project_id?: string, next_cursor?: string, include_usage_count?: boolean }
- `POST https://api.mcp.ai/api/futureagi/list/annotation/queues` — List one page of FutureAGI annotation queues by status or name, optionally including item counts. Returns next_cursor to continue.
  - body: { search?: string, status?: string, page_size?: integer, next_cursor?: string, include_counts?: boolean }
- `POST https://api.mcp.ai/api/futureagi/list/custom/eval/configs` — List custom evaluation configurations, optionally restricted to a FutureAGI project or evaluation task.
  - body: { task_id?: string, project_id?: string }
- `POST https://api.mcp.ai/api/futureagi/list/datasets` — List one page of datasets in the connected FutureAGI organization, optionally searching by name. Returns next_cursor to continue.
  - body: { page_size?: integer, next_cursor?: string, search_text?: string }
- `POST https://api.mcp.ai/api/futureagi/list/eval/tasks` — List one page of FutureAGI evaluation tasks, optionally filtering by project ID or task name. Returns next_cursor to continue.
  - body: { name?: string, page_size?: integer, project_id?: string, next_cursor?: string }
- `POST https://api.mcp.ai/api/futureagi/list/personas` — List one page of built-in and workspace personas for FutureAGI simulations, with type, simulation-mode, and text filters. Returns next_cursor to continue.
  - body: { type?: string, limit?: integer, search?: string, next_cursor?: string, simulation_type?: string }
- `POST https://api.mcp.ai/api/futureagi/list/run/tests` — List one page of configured FutureAGI run tests without executing them, optionally filtering by name, source type, or prompt template. Returns next_cursor to continue.
  - body: { limit?: integer, search?: string, next_cursor?: string, simulation_type?: string, prompt_template_id?: string }
- `POST https://api.mcp.ai/api/futureagi/list/scenarios` — List one page of FutureAGI simulation scenarios, optionally filtering by agent definition, agent type, or search text. Returns next_cursor to continue.
  - body: { limit?: integer, search?: string, agent_type?: string, next_cursor?: string, agent_definition_id?: string }

## Example prompts
- "What can I do in FutureAGI?"
- "Show me a summary of my FutureAGI account"

## More
- Page: https://mcp.ai/futureagi
- Agent spec (llms.txt): https://mcp.ai/futureagi/llms.txt
- Postman collection: https://mcp.ai/futureagi/postman.json