# Moderation API — MCP server on mcp.ai
> Connect your Moderation API account and use 11 tools for AI safety and compliance straight from your AI agent. Connect with your own API key. Moderation API provides content detection, human review workflows, author management, and moderation actions for online platforms.

By: mcp.ai · official
Page: https://mcp.ai/moderationapi

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_moderationapi?ms=1787293740000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/moderationapi/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/moderationapi/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/moderationapi/skill.md
Postman collection (v2.1): https://mcp.ai/moderationapi/postman.json

## Tools
- moderationapi_evaluate_content(channel?: string, content: object, metadata?: object, author_id?: string, meta_type?: string, timestamp?: number, content_id?: string, client_action?: object, conversation_id?: string) — Evaluate content without retaining it or adding it to a review queue, and return policy findings and the recommended moderation action.
- moderationapi_execute_action(value?: string, queue_id?: string, action_key: string, author_ids?: string[], content_ids?: string[], duration_ms?: number) — Apply a discovered moderation action to content items or authors. Actions can reject content or block or suspend authors and may be irreversible; inspect LIST_ACTIONS before calling.
- moderationapi_get_account() — Return the connected Moderation API account, plan, current project, and current quota values.
- moderationapi_get_review_queue(queue_id: string) — Return metadata and item counts for a review queue by ID. Requires the paid review-queue add-on; contact Moderation API sales if review queues are not enabled for the connected organization.
- moderationapi_get_wordlist(wordlist_id: string) — Return one wordlist and its current words by ID.
- moderationapi_list_actions(queue_id?: string) — List moderation actions available to the organization, optionally restricted to a review queue.
- moderationapi_list_review_queue_items(cursor?: string, queue_id: string, author_id?: string, page_size?: integer, sort_field?: string, sort_direction?: string, include_resolved?: boolean) — List and filter one page of moderation items in a review queue. Requires the paid Moderation API review-queue add-on.
- moderationapi_list_wordlists() — List the organization's wordlists and their identifiers.
- moderationapi_modify_wordlist_words(words: string[], operation: string, wordlist_id: string) — Add words to or remove words from an existing wordlist.
- moderationapi_set_review_queue_item_status(status: string, comment?: string, item_id: string, queue_id: string) — Mark a review queue item resolved or return it to pending. Requires the paid review-queue add-on.
- moderationapi_submit_content_for_moderation(channel?: string, content: object, metadata?: object, author_id?: string, meta_type?: string, timestamp?: number, content_id?: string, client_action?: object, conversation_id?: string) — Evaluate content and allow Moderation API to retain it and add it to a review queue according to the project's configuration.

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

## Links
Docs: https://mcp.ai/docs/mcps/moderationapi
Website: https://mcp.ai/mcps/moderationapi