Compliance

This is the Compliance demo. Every visitor shares this company, and it resets every night.

What you change here, everyone sees until the next reset. Email, payments, and the AI models are switched off.

Start your own trial
  • EU GDPR (2016)
  • ISO 27001:2022
  • NIS2
  • NIS2 Netherlands (Cbw, 2026)

Nothing found that matches the search criteria.

Start your own trial
SV
Sam de Vries
sam.devries@tidewell-it.example

Any MCP client

API & Agent Access

The address

Compliance runs an MCP server at this address:

https://demo.mvdm.io/compliance/mcp

It speaks the Streamable HTTP transport. It also answers the older initialize handshake, so a client built for an earlier revision of MCP can connect too. The server keeps no session between calls. It offers tools and a short set of instructions for the Agent. The server tells your Agent which tools it has, so this guide does not list them.

Your Agent acts as you, in one Account at a time, with everything you can do in Compliance. Its changes show up in History under your name.

Signing in

Most clients sign in through your browser. Add the address to your client and let it connect. Compliance tells the client where to sign in, and the client does the rest:

  1. The first call has no credential, so the server answers 401. The answer points to the server's Protected Resource Metadata at https://demo.mvdm.io/compliance/.well-known/oauth-protected-resource/mcp, which names Auth, the mvdm.io sign-in service.
  2. The client introduces itself to Auth. It either registers itself with Dynamic Client Registration, or sends the address of its Client ID Metadata Document.
  3. The client opens Auth in your browser. It uses the authorization code flow with PKCE (S256) and names the MCP address as the resource.
  4. You sign in, if you are not signed in already.
  5. Auth gives the client an access token and a refresh token. The client refreshes the access token on its own. A connection that nobody uses for 90 days ends.

The consent page

Before your Agent gets access, Auth shows a consent page:

  • It names the Agent. For a client that registered itself, it says the name is the one the Agent gave, which Auth cannot check. For a client with a metadata document, it names the domain that sent it.
  • It warns that the Agent gets all your power, in every Account you belong to, billing and the License included.
  • It asks which Account the Agent starts in.

Press Allow, then go back to your Agent and ask it something about your Compliance work.

You can see and end every connection on API & Agent Access. An ended connection fails on its next call.

A Personal token instead

If your client cannot sign in through a browser, use a Personal token:

  1. Open API & Agent Access and create a Personal token. Choose its name, the Account it starts in, and when it expires.
  2. Copy the token. It is shown only once.
  3. Set your client to send it on every request as this header:
Authorization: Bearer <token>

A Personal token acts as you, like a browser sign-in does. Keep it secret, and end it on API & Agent Access when you no longer need it.

A request that carries an Origin header for a site other than Compliance is refused, to protect against DNS rebinding. Desktop and command-line clients send no such header, so this does not affect them.

What to expect

  • Browser handoff. Some acts need you in the browser, such as anything that costs money or accepting the Legal terms. Your Agent then shows you a link. Open it, check what is filled in, and confirm. If you do not open the link, nothing happens.
  • Upload link. A tool call cannot carry a file, so your Agent asks Compliance for an Upload link, a one-time address for one file. The Agent sends the file there itself, often with curl, or it shows you the link so that you can pick the file in your browser. The link expires after a few minutes.
  • One Account at a time. Your Agent starts in the Account you chose on the consent page, or the one you chose for your Personal token. Every answer says which Account it acted in. Ask your Agent to switch, and it moves to another Account you belong to.
  • Rate limit. Each User has a limit on calls per minute, shared by all of your Agents and scripts. Over the limit, a call fails and says how many seconds to wait.

Another way in

Compliance also has a command-line tool, the Compliance CLI. It suits Agents that run commands, and scripts. See the CLI guide.

Are you sure?

This action cannot be reverted.

Leave this page?

Your changes on this form are not saved. If you leave, they are lost.