Academy & HelpAPI & developers

Typetone MCP server: reference

Connect Claude, ChatGPT, Claude Code, Cursor or Codex to Typetone. Check content, run audits and review violations from your AI assistant.

The Typetone MCP server lets an AI assistant work with your Typetone workspace. From Claude, ChatGPT or a coding tool you can check a draft against your rules, start a compliance audit, and review the violations an audit found, without opening the Typetone app.

This page is the technical reference. For a general introduction, see API, MCP and using Typetone in your AI tools.

Server details

Server URLhttps://api.app.typetone.ai/mcp/
TransportStreamable HTTP
AuthenticationOAuth 2.1 with PKCE, or an API key
AccessWorkspaces on the Enterprise plan
ScopeOne workspace: the one you sign in to, or the one your API key belongs to

Connect Claude, ChatGPT and other AI apps

AI apps that support custom connectors sign you in with OAuth. You don’t need an API key.

  1. Add a custom connector in your AI app. In Claude, go to Settings → Connectors.
  2. Paste the server URL: https://api.app.typetone.ai/mcp/
  3. When asked, sign in with your Typetone account.

Everything the assistant does then runs as you. Review decisions and comments are saved under your name, just like when you work in the app.

Connect Claude Code, Cursor and Codex

Coding tools can send an API key as a header. Create a key in the Typetone app under Settings → MCP & API. That page also generates a ready-to-paste install command for Claude Code, Cursor, Codex and Gemini CLI.

claude mcp add --transport http typetone https://api.app.typetone.ai/mcp/ \
  --header "Authorization: Bearer YOUR_API_KEY"

Send the key as Authorization: Bearer <key> or as X-API-Key: <key>. Treat it like a password: keep it out of shared code and revoke it in the app when you no longer need it.

Actions taken with an API key are recorded for the workspace, not for a specific person. Reviewers who label violations should connect with OAuth so decisions carry their own name.

Authentication details

For client developers and connector directories:

  • OAuth 2.1 authorization code flow with PKCE (S256). Public clients only (token_endpoint_auth_method: none).
  • Dynamic client registration is supported.
  • Protected resource metadata: https://api.app.typetone.ai/.well-known/oauth-protected-resource/mcp
  • Authorization server metadata: https://api.app.typetone.ai/.well-known/oauth-authorization-server
  • Scopes: mcp:connect and offline_access.
  • Access tokens are valid for one hour. Refresh tokens are valid for 30 days and rotate on every use.
  • An unauthenticated request returns 401 with a WWW-Authenticate header that points to the metadata above.
  • Access is checked on every request: a user who leaves the workspace, or a workspace that leaves the Enterprise plan, loses access right away.

Tools

ToolWhat it doesChanges dataUses credits
list_brand_voicesLists the brand voices in the workspaceNoNo
get_brand_voiceReturns the guidelines of one brand voiceNoNo
list_content_rulesLists the compliance and brand rules content is checked againstNoNo
check_contentChecks a text against the workspace’s rules and returns violations with a recommended fixNoYes
get_credit_balanceReturns the remaining credit balanceNoNo
list_rulesetsLists the rulesets (rule groups) available for auditsNoNo
list_assetsLists or searches assets in the Asset VaultNoNo
audit_assetsStarts a compliance audit of up to 10 assets against one rulesetYesYes
get_audit_resultsReturns the progress and violations of an auditNoNo
list_auditsLists the workspace’s audits, newest firstNoNo
list_violationsPages through the violations of one audit, filtered by review state, severity or search termNoNo
get_violationReturns one violation in full: flagged text, reason, rule, recommended fix, suggested text and commentsNoNo
review_violationRecords a review decision on a violationYesNo
comment_on_violationAdds a comment to a violation’s thread. Mentions in the comment don’t assign the violation; assign in the app.YesNo

Review an audit from your AI assistant

Compliance reviewers can work through an audit in a conversation instead of in the app. A typical session:

  1. “Show me my latest audits.” The assistant calls list_audits.
  2. “Let’s review the undecided violations of the one from Monday.” The assistant calls list_violations, which shows undecided violations first.
  3. For each violation the assistant shows the flagged text, why it was flagged and the recommended fix (get_violation).
  4. You decide, and the assistant records it with review_violation.

review_violation takes one of these actions:

ActionMeaning
dismissNot a real violation. A reason is required, and it’s saved with the decision. Other actions don’t take a reason: add a comment instead.
elevated_riskA real violation with elevated risk.
urgent_violationA real violation that needs action now.
mark_fixedThe fix has been checked and the violation is resolved.
reopenBack to undecided. Clears an earlier decision.

Set apply_to_group to true to apply the same decision to every violation with the same group_id: the same finding on several assets.

Decisions follow the same rules as in the app. They show up right away in the audit’s review mode, with the reviewer’s name in the activity trail. A violation that is assigned to a colleague can only be dismissed or marked fixed by that colleague, the person who assigned it, or an admin.

Credits and limits

  • check_content and audit_assets use workspace credits. Reading data and recording review decisions is free.
  • audit_assets asks for confirmation when an audit’s estimated cost is large. The assistant then repeats the call with the returned estimate_id.
  • Credit-using tools are limited to 20 calls per minute and 3 at a time per workspace.
  • check_content accepts up to 60,000 characters per call.
  • list_violations returns up to 50 violations per page.

REST API

The same review actions are available over the REST API, for your own scripts and systems. Base URL: https://api.app.typetone.ai/public/v1. Send your API key in the X-API-Key header.

MethodPathWhat it does
GET/auditsList audits, newest first
GET/audits/{audit_id}/violationsList violations, with review_state, severity, search, page and page_size
GET/violations/{violation_id}Get one violation with its comments
POST/violations/{violation_id}/reviewRecord a decision: {"action": "dismiss", "reason": "..."}
POST/violations/{violation_id}/commentsAdd a comment: {"comment": "..."}

The full, interactive reference is at api.app.typetone.ai/public/docs.

Example prompts

  • “Check this LinkedIn post against our brand and compliance rules, and fix what’s wrong.”
  • “Does this landing page copy contain green claims we can’t back up?”
  • “Audit the three newest pages in our Vault against our marketing compliance ruleset.”
  • “Walk me through the undecided violations of our latest audit, most severe first.”
  • “Mark this one as an urgent violation and add a note that legal needs to see it.”

Frequently asked questions

Do I need an API key to use Typetone in Claude or ChatGPT?

No. Add Typetone as a custom connector with the server URL and sign in with your Typetone account. API keys are for tools that take a request header, like Claude Code, Cursor and Codex.

Can the assistant dismiss violations on its own?

The review tools tell the assistant to record only decisions you made or confirmed. Every decision is saved under the name of the signed-in user and shows up in the audit's activity trail, so a reviewer can see and undo it in the Typetone app.

Which data can the MCP server reach?

Only the workspace you signed in to (or that your API key belongs to): its brand voices, rules, assets, audits and violations. It cannot reach other workspaces.

Does using the MCP server cost credits?

Reading data and recording review decisions is free. check_content and audit_assets run AI analysis and use workspace credits, just like in the app.

Automated content auditing and compliance at enterprise scale.

Enterprise ready integrations, regulatory database and onboarding included.

Join 100.000+ marketing & compliance experts who use Typetone.

Before: 1,284 live violations After: 0 violations
European servers Data privacy safe