> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.markup.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.markup.ai/_mcp/server.

# Running Agents

> Discover, run, and track Markup AI content agents via the REST API.

Markup AI's content agents are exposed through the **Agents** endpoints of the API. Each agent runs against the settings configured for your organization in the [Markup AI console](https://console.markup.ai) — no per-call style guide IDs. For what each agent does and why it matters, see the [Agent Catalog](/agents).

## The run flow

1. **Discover** the agents available to your organization with `GET /agents`. Each entry includes the agent's stable `name` (e.g. `brand_voice`), its `id`, description, and category. Resolve the `id` from the `name` at runtime — every agent page below has copy-paste examples that do exactly that.
2. **Run** an agent with `POST /agents/{agent_id}/run`, passing your content as `text`. Pass `wait=true` to block until the run completes; otherwise the response returns immediately with a `workflow_id`.
3. **Track** longer runs with `GET /agents/workflows/{workflow_id}`, stream progress from `GET /agents/workflows/{workflow_id}/stream` (server-sent events), or supply a `webhook_url` in the run request to receive the result when the agent finishes.

> **Note**
>
> The agents returned by `GET /agents` depend on your organization's plan and feature access.

## Agent reference

| Agent                                                        | API `name`           | Category          |
| ------------------------------------------------------------ | -------------------- | ----------------- |
| [AI Voice](/developer/agents/ai-voice-detector)              | `ai_voice_detector`  | Content Integrity |
| [Brand Terms](/developer/agents/terminology)                 | `terminology`        | Brand             |
| [Brand Voice](/developer/agents/brand-voice)                 | `brand_voice`        | Brand             |
| [Claims](/developer/agents/generic-claims)                   | `generic_claims`     | Accuracy          |
| [Date & Time Accuracy](/developer/agents/date-time-accuracy) | `date_time_accuracy` | Accuracy          |
| [Fluff](/developer/agents/focus-agent)                       | `focus_agent`        | Content Integrity |
| [Freshness](/developer/agents/freshness)                     | `freshness`          | AI Visibility     |
| [Key Takeaways](/developer/agents/key-takeaways)             | `key_takeaways`      | AI Visibility     |
| [Link Integrity](/developer/agents/link-integrity)           | `link_integrity`     | Accuracy          |
| [Persona](/developer/agents/persona)                         | `persona`            | Brand             |
| [Q\&A Optimization](/developer/agents/answer-authority)      | `answer_authority`   | AI Visibility     |
| [Sentence Clarity](/developer/agents/sentence-clarity)       | `sentence_clarity`   | Content Integrity |
| [Snippet Readiness](/developer/agents/snippet-readiness)     | `snippet_readiness`  | AI Visibility     |
| [Source Authority](/developer/agents/source-authority)       | `source_authority`   | AI Visibility     |
| [Style](/developer/agents/style-agent)                       | `style_agent`        | Brand             |

## Via MCP

The same agents run on the hosted MCP server at `https://api.markup.ai/mcp/`, addressed by the same `name` used here. Ask for a review and `markupai_review` picks the agents for you, or name them explicitly with `markupai_run_agents` — see the [MCP overview](/mcp) to connect Claude, Cursor, or any other MCP client.