> 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.

# Claims

> Catch risky claims before compliance does.

**Accuracy**

**Catch risky claims before compliance does.** This agent flags bold or unsubstantiated claims that may carry compliance risk.

## What it catches

Strong outcome claims without evidence, promissory language, and other assertions that compliance or credibility review would flag — each labeled with its risk type. The [Source Authority](/agents/source-authority) covers the complementary problem: missing attribution.

## Why it matters

An unsubstantiated "guaranteed results" costs more than a rewrite — it can cost legal review cycles or worse. Catching risky language at draft time keeps publishing fast and safe.

#### [Markup AI for Google Docs](/apps/google-docs)

The fastest way to use this agent: catch and fix issues right inside Google Docs, with the Markup AI Chrome Extension.

#### [Use it in your AI assistant](/mcp)

Available on Markup AI's hosted MCP server as `generic_claims` — or ask for a review and let Markup AI select it.

#### [Run it via the API](/developer/agents/generic-claims)

Resolve the agent by name and run it with one call — full examples in the Agent Reference.