Moderation API
Server Details
Let AI agents run your Moderation API account: triage review queues, investigate authors, tune policies and wordlists, respond to incidents and report on moderation.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- Moderation API
TDQS
Scored across 58 tools
Most tools are cleanly separated by resource and action, especially projects, channels, webhooks, wordlists, and analytics. The main ambiguity is that generic actions-execute overlaps with convenience tools like content-allow, content-reject, authors-block, authors-suspend, and authors-unblock, though the descriptions clarify the distinctions.
The set mostly follows a hyphenated resource-action convention such as actions-create, authors-list, and webhooks-retrieve. There are minor deviations with get versus retrieve and compound names like queue-get-stats, projects-api-keys-create, and wordlist-get-embedding-status, but the pattern remains readable.
With 58 tools, the surface is very large for an agent to navigate and select from reliably. Although the tools are grouped by resource, the count is well beyond a well-scoped MCP toolset and adds substantial selection overhead.
The API covers many CRUD operations across projects, channels, authors, actions, queues, webhooks, and wordlists, plus moderation submission and analytics. However, central moderation concepts such as policies and rules lack management tools, and there is little content retrieval/list/delete coverage, creating notable gaps.
Publisher details
- Operator
- Moderation Labs · Publisher source
- Operator website
- https://moderationapi.com · Publisher source
- Vendor relationship
- First-party · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Not available
Available Tools
58 toolsaccount-retrieveCRead-onlyInspect
Get account details
Get account details
Inputs: request.
actions-createAInspect
Create an action
Create an action that reviewers and rules can take. type sets what it does: a built-in type changes the item or author in Moderation API, and a custom type (ITEM_CUSTOM, AUTHOR_CUSTOM) only records the decision for the webhooks to deliver. Creating an action does not execute it.
Inputs: request (required).
actions-deleteADestructiveInspect
Delete an action
Delete an action and all of its webhooks.
Inputs: request (required).
actions-executeADestructiveInspect
Execute moderation action
Execute one action of the project, by ID or key, on content items or authors. A built-in action changes them in Moderation API (for example rejects the items or blocks the authors). Every executed action is recorded, and the project sends it to the webhooks of the action and to its other webhook endpoints, where the customer platform can act on it. List the actions first to see what each one does.
Inputs: request (required).
actions-listBRead-onlyInspect
List moderation actions
List the moderation actions of the project, with their webhooks. An action is a decision that a reviewer or a rule can take on content or an author. Built-in actions (for example reject an item or block an author) change the item or author in Moderation API. Custom actions record the decision and send it to the webhooks of the action, where the customer platform acts on it. The list is paginated.
Inputs: request.
actions-retrieveARead-onlyInspect
Get an action
Get an action by ID: its type, where it shows in the review queues, the values it takes and its webhooks.
Inputs: request (required).
actions-updateADestructiveInspect
Update an action
Update the settings of an action: its name, type, queues and values. The new settings apply the next time the action is executed. Updating an action does not execute it.
Inputs: request (required).
analytics-authorsBRead-onlyInspect
Get the most flagged authors
Get the authors with the most flagged content in a time window, largest first.
Inputs: request.
analytics-automationARead-onlyInspect
Get the automation breakdown
Get how flagged content was handled in a time window: settled by rules or the casebook, or sent to human review, and what the reviewers decided.
Inputs: request.
analytics-channelsARead-onlyInspect
Get analytics per channel
Get requests, flags and flag rate for each channel of the project in a time window.
Inputs: request.
analytics-policiesBRead-onlyInspect
Get the most flagged policies
Get the policy labels that flagged the most content in a time window, largest first, with the count in the window before.
Inputs: request.
analytics-summaryBRead-onlyInspect
Get the analytics summary
Get the totals of the project for a time window: requests, flags, flag rate, allowed, rejected and sent to review, with the window before for the trend. Also the review queue backlog and a flag-rate spike, if there is one.
Inputs: request.
analytics-volumesBRead-onlyInspect
Get volumes over time
Get requests, flags, rejections and reviews per hour (24h) or per day (7d, 30d, 90d), oldest first.
Inputs: request.
authors-blockBDestructiveInspect
Block author
Block an author with the built-in block action. A blocked author cannot post new content until unblocked.
Inputs: request (required).
authors-createBInspect
Create a new author
Create a new author. Typically not needed as authors are created automatically when content is moderated.
Inputs: request (required).
authors-deleteADestructiveInspect
Delete an author
Delete a specific author. This resets the author: status, blocks, trust level, metrics and action history are removed. The author is created again with a clean record the next time content is moderated for the same ID.
Inputs: request (required).
authors-listBRead-onlyInspect
List authors
List the authors of the project, with their status, trust level and content metrics. The list is paginated. By default, the authors that were active most recently come first.
Inputs: request.
authors-retrieveBRead-onlyInspect
Get author details
Get detailed information about a specific author including historical data and analysis
Inputs: request (required).
authors-suspendBDestructiveInspect
Suspend author
Block an author for a limited time with the built-in suspend action.
Inputs: request (required).
authors-unblockBInspect
Unblock author
Unblock a blocked or suspended author with the built-in unblock action, so they can post new content again.
Inputs: request (required).
authors-updateCDestructiveInspect
Update author details
Update the details of a specific author
Inputs: request (required).
channels-createAInspect
Create a channel
Create a channel in a project, with the default rules. The project's first channel becomes its default. Needs the channels:write permission.
Inputs: request (required).
channels-deleteADestructiveInspect
Delete a channel
Delete a channel. Its key is freed for a new channel. When it was the default, the oldest remaining channel becomes the default. A channel that still moderates a Slack workspace must be disconnected first. Needs the channels:write permission.
Inputs: request (required).
channels-duplicateAInspect
Duplicate a channel
Copy a channel in its project, with every setting, policy, rule and wordlist. Integrations (Discord, Slack, WordPress) are not copied. Needs the channels:write permission.
Inputs: request (required).
channels-listARead-onlyInspect
List channels
List the channels in a project. The list is paginated. Needs the channels:read permission.
Inputs: request (required).
channels-retrieveBRead-onlyInspect
Get a channel
Get a channel by ID. Needs the channels:read permission.
Inputs: request (required).
channels-updateADestructiveInspect
Update a channel
Update a channel. Fields you leave out keep their value. Needs the channels:write permission.
Inputs: request (required).
content-allowCInspect
Allow content
Allow a content item with the built-in allow action, and resolve it in the review queue.
Inputs: request (required).
content-rejectCDestructiveInspect
Reject content
Reject a content item with the built-in reject action, and resolve it in the review queue.
Inputs: request (required).
content-submitAInspect
Submit content
Moderate one piece of content: text, an image, a video, audio or an object with several fields. The project checks it against the policies of its channel and returns the result. Act on recommendation.action (allow, review or reject). The content is stored in the project unless doNotStore is set, and items to review go to the review queue. The project can send the result to its webhook endpoints.
Inputs: request (required).
feedback-createAInspect
Send feedback
Sends a feature request, bug report or other feedback to the Moderation API team. The team reads every request and can reply by email. Limited to 5 requests per minute per organization.
Inputs: request (required).
projects-api-keys-createAInspect
Create a project API key
Create a new secret API key for a project and return it. Give each app or computer its own key, so you can revoke one without breaking the others. The project's existing keys keep working. Needs the projects:write permission.
Inputs: request (required).
projects-createAInspect
Create a project
Create a project with one channel, a review queue inbox and a secret API key. Give a domain or context and the project suggests policies for the platform. Needs the projects:write permission and a key that reaches all projects.
Inputs: request (required).
projects-deleteADestructiveInspect
Delete a project
Delete a project with everything in it: channels, queues, API keys and stored content. This can't be undone. The project's API keys stop working at once. Needs the projects:write permission.
Inputs: request (required).
projects-duplicateAInspect
Duplicate a project
Copy a project's configuration into a new project: its settings, every channel with its policies, rules and wordlists, its moderation actions and its review queues. The copy gets its own secret API key. Webhooks, integrations, API keys and content are not copied. Needs the projects:write permission and a key that reaches all projects.
Inputs: request (required).
projects-listBRead-onlyInspect
List projects
List the projects in the organization. The list is paginated. Needs the projects:read permission.
Inputs: request.
projects-retrieveBRead-onlyInspect
Get a project
Get a project by ID. Needs the projects:read permission.
Inputs: request (required).
projects-updateCDestructiveInspect
Update a project
Update a project. Fields you leave out keep their value. Needs the projects:write permission.
Inputs: request (required).
queue-get-statsBRead-onlyInspect
Get queue statistics
Get review statistics of a queue for a period: resolved and pending items, the top reviewers and the resolved items per day.
Inputs: request (required).
queue-items-listBRead-onlyInspect
List queue items
List the items of a review queue, with the filters and the date window of the queue applied. By default only pending items. The list is paginated. Use the item id or contentId to resolve or unresolve an item.
Inputs: request (required).
queue-items-resolveAInspect
Resolve a queue item
Mark an item of a queue as resolved. It is the same as a check-off in the dashboard: the item leaves the pending list and a QUEUE_ITEM_COMPLETED webhook is sent. itemId is the item id or your contentId. To also take a moderation action, use POST /actions/execute.
Inputs: request (required).
queue-items-resolve-manyAInspect
Resolve queue items
Mark up to 100 items of a queue as resolved in one request. Each item is resolved the same as with POST /queue/{id}/items/{itemId}/resolve, and each ID is an item id or your contentId. IDs that match no item in the project are skipped and returned in notFoundIds.
Inputs: request (required).
queue-items-unresolveAInspect
Unresolve a queue item
Mark a resolved item of a queue as pending again. It is the same as removing a check-off in the dashboard: the item comes back in the pending list. itemId is the item id or your contentId.
Inputs: request (required).
queue-listBRead-onlyInspect
List queues
List the review queues of the project. The default queue comes first. The list is paginated. To get the item counts of a queue, use GET /queue/{id}.
Inputs: request.
queue-retrieveBRead-onlyInspect
Get a queue
Get a review queue with its item counts. The counts use the filters and the date window of the queue, the same as the dashboard.
Inputs: request (required).
webhooks-createAInspect
Create a webhook
Create a webhook subscribed to one or more event types. Deliveries use the v2 envelope and are signed with the project signing secret (see the signing secret endpoint).
Inputs: request (required).
webhooks-deleteDDestructiveInspect
Delete a webhook
Delete a webhook.
Inputs: request (required).
webhooks-listBRead-onlyInspect
List webhooks
List the webhooks of the project. The list is paginated.
Inputs: request.
webhooks-retrieveCRead-onlyInspect
Get a webhook
Get a webhook by ID.
Inputs: request (required).
webhooks-updateADestructiveInspect
Update a webhook
Update a webhook. Legacy v1 webhooks are read-only: delete them and create a new webhook instead.
Inputs: request (required).
wordlist-createAInspect
Create wordlist
Create a wordlist in the organization. You can add words now or later. Each word is embedded in the background for similarity matching. Use the embedding status endpoint to follow the progress. To use the wordlist in moderation, add it to a policy.
Inputs: request (required).
wordlist-deleteADestructiveInspect
Delete wordlist
Delete a wordlist and its words. Channels that use the wordlist do not block the delete: the wordlist is removed from their policies. detachedChannelIds lists those channels. This cannot be undone.
Inputs: request (required).
wordlist-get-embedding-statusCRead-onlyInspect
Get embedding status
Get the current embedding progress status for a wordlist
Inputs: request (required).
wordlist-listCRead-onlyInspect
List wordlists
List the wordlists of the organization. The list is paginated.
Inputs: request.
wordlist-retrieveCRead-onlyInspect
Get wordlist
Get a specific wordlist by ID
Inputs: request (required).
wordlist-updateADestructiveInspect
Update wordlist
Update a wordlist. Fields that you do not send stay the same. If you send words, they replace all existing words, and the embeddings are updated in the background.
Inputs: request (required).
wordlist-words-addCInspect
Add words to wordlist
Add words to an existing wordlist
Inputs: request (required).
wordlist-words-removeCDestructiveInspect
Remove words from wordlist
Remove words from an existing wordlist
Inputs: request (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm46 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.