# Markup AI — how to use (mcp.ai)

Connect your Markup AI account and use 10 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Markup AI provides content agents, brand terminology, personas, brand voice profiles, and style configuration for evaluating and improving content.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_markup_ai?ms=1787291280000`
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. `markup_ai_get_agent`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/markup_ai`
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/markup_ai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/markup_ai/get/agent` — Get one agent's metadata and complete runtime input and output JSON Schemas before executing it.
  - body: { agent_id: string }
- `POST https://api.mcp.ai/api/markup_ai/get/analysis/profile` — Get one persona, brand voice profile, style target, or style guide by ID, including detailed configuration needed to understand its effect on analysis. Style details can contain a large hierarchy of g
  - body: { profile_id: string, profile_type: string }
- `POST https://api.mcp.ai/api/markup_ai/get/workflow` — Get the current status and result of an asynchronous agent workflow by ID.
  - body: { workflow_id: string }
- `POST https://api.mcp.ai/api/markup_ai/list/agent/categories` — Return all agent categories available to the connected organization for discovery and agent-list filtering.
- `POST https://api.mcp.ai/api/markup_ai/list/agents` — Discover Markup AI agents available to the connected organization, optionally filtered by category. Returns compact summaries for choosing an agent; use GET_AGENT for its full runtime schemas.
  - body: { category?: string, page_size?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/markup_ai/list/analysis/profiles` — List selectable persona, brand voice, style guide, style target, or content profile resources used to configure agent runs.
  - body: { profile_type: string }
- `POST https://api.mcp.ai/api/markup_ai/list/terminology/resources` — List terminology term sets or domains with filters and cursor-controlled pagination.
  - body: { search?: string, page_size?: integer, domain_ids?: string[], has_context?: boolean, next_cursor?: string, resource_type: string }
- `POST https://api.mcp.ai/api/markup_ai/list/workflows` — List one cursor-controlled page of agent execution workflows, optionally filtering that page by status, stable agent name, or creation time.
  - body: { limit?: integer, status?: string, agent_name?: string, next_cursor?: string, created_after?: string }
- `POST https://api.mcp.ai/api/markup_ai/run/agent` — Run one selected Markup AI agent against document text, synchronously or asynchronously. Discover the agent and inspect its schema first; execution may consume organization quota. The persona agent re
  - body: { url?: string, goal?: string, text: string, wait?: boolean, agent_id: string, domain_ids?: string[], persona_id?: string, webhook_url?: string, document_ref?: string, document_name?: string, style_guide_id?: string, voice_profile_id?: string, content_profile_id?: string }
- `POST https://api.mcp.ai/api/markup_ai/search/terminology` — Find organization terminology rules relevant to supplied text, optionally limited to selected domains.
  - body: { text: string, domain_ids?: string[] }

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

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