Apparently MCP · Connector setup

Put regulatory steering inside the agent writing your product.

Name: Apparently
Availability: PreOrder

Connect the live Apparently MCP endpoint to Claude Code, Claude, ChatGPT, or any compatible agent. The connection status below distinguishes what works now from what still requires Apparently OAuth.

Remote MCP endpointhttps://www.apparently.cc/mcp

Not checked yet · run a live tools/list request without sending a credential.

Chat + Cowork

Connect Apparently to Claude

Header beta

Activation path

Choose the secure authentication path supported by your workspace.

Download setup

Hosted Claude remains a conditional beta path.

Static request-header support depends on the Claude plan and workspace; this deployment does not currently report Apparently OAuth ready.

Confirm connector permissions
A workspace owner may need to enable custom connectors before a member can add Apparently.
Add the remote MCP endpoint
In Claude, open Settings or Customize → Connectors → Add custom connector and enter the Apparently endpoint.
Authenticate without exposing the key
If your account offers beta static request headers, add Authorization: Bearer with your Apparently API key. Never connect the tool as authless.
Enable it for the conversation
Turn on Apparently in Chat or Cowork and use the test prompt below after the required authentication path succeeds.

Create API key Official setup docs

Connection readinessWhat is live today

Remote MCP endpoint: Live
Bearer API keys: Live
Apparently OAuth: Status unavailable

Claude Code and custom clients that accept request headers work now. Hosted provider readiness is read from this deployment; plan and administrator controls still determine whether each user can add the connector.

ConfigurationHosted Claude connection

Name: Apparently
Remote MCP URL: https://www.apparently.cc/mcp
Authorization: Bearer YOUR_APPARENTLY_API_KEY

Tools returned by the live endpointFour governed actions

evaluate_actionReview a code change, command, or deployment before execution.
evaluate_changesetReview a whole diff or commit at once, rather than file by file.
legal_advisoryAnalyze a regulatory or legal question with controls and confidence.
escalate_to_legalRoute a material judgment to the appropriate human legal queue.
escalation_statusRetrieve the current status and resolution of an escalation.

Connection testTry this after activation

Before changing payments/loyalty.ts to redeem purchased points for cash, evaluate the change across every planned launch jurisdiction. Return the legal issue, authority, safer code paths, required licences, approvals, and citations. Do not execute or merge until the route is authorized.

The agent should call evaluate_action before proposing a release.

Apparently coding workspacePrefer a governed coding agent with Apparently already in the loop?Sign In to Code