Give your AI agent a desk here, not a copy of the files.
Connect Claude, Cursor, or anything else that speaks the Model Context Protocol. It works on the same records you do, under the same permissions, and every change it makes is a change you can see.
What it gets
92 tools against your real records.
Not a chat window with your documents pasted in. Named actions your agent calls directly, on the same brands, content, records and contacts you work on in the studio.
Draft, revise and schedule the content your brand publishes, in the same queue you review.
Read and write the hierarchy your product is described by, down to individual fields.
Open a working document, add to it, and link it to the records it belongs with.
Look people up, log what happened, and move them through a pipeline.
One typo-tolerant search across the workspace, ranked, instead of guessing at names.
Read what other agents worked out before, and write down what this one learned.
Connect
Two ways in, both about a minute.
Setup happens in your client, not in m18t. There is no agent screen to configure here. You point a client at the address below and approve it.
If your client supports it, use this one.
Add the address as a remote server. The client sends you here to sign in, shows you which application is asking, and you approve it. No token to copy, nothing secret sitting in a config file, and you can withdraw it later.
https://m18t.com/mcp
For clients that want a header.
Create a token in your account settings, decide there whether it can write and which brands it can reach, and paste it into your client. Revoke it on its own whenever you want.
{
"mcpServers": {
"m18t": {
"url": "https://m18t.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}Then tell it to get its bearings. Your agent can ask the workspace to orient it, and gets back the brands it is allowed to see, the vocabulary, and how records link together. You do not write that briefing or keep it current. Full setup guide.
The part that matters
An agent gets exactly what its person has.
Not a shared key in a config file. Every token belongs to one person, and that person's checks run for the agent on every single call.
Issued to a named person and revocable on its own. Never a shared credential.
Hand it a token that cannot write. Checked on our side, not asked for in a prompt.
If they cannot see it, neither can the agent. No prompt talks it into more.
Combined with what its person can already reach, so the scope only ever shrinks.
No action hands back a stored key. There is nothing to ask for.
No open ended queries, no arbitrary commands. The list is the whole surface.
What an agent deliberately cannot do here.
These are decisions, not gaps. An agent that can quietly delete your work is not a feature, and neither is one that can post to your audience without you.
There is no delete action. If something needs removing, a person removes it.
It drafts and schedules where you would. Pushing live is not wired to agents.
It can tell you a key is missing. Connecting one is yours.
You get a plain answer instead of a creative workaround.
Your agents remember. You approve what they remember.
An agent that quietly writes its own assumptions into a memory nobody reads is a liability. So what it writes starts as a proposal, and nothing recalls it until you confirm it.
It writes down what it worked out, marked as a proposal.
Proposals sit in one place, in plain words.
Only what you confirm is ever recalled. The rest stays inert.
Recall is keyword matching across the memories you confirmed. It is not a system that infers meaning, and we are not going to describe it as one.
Questions people actually ask
What is the Model Context Protocol?
An open standard for connecting an AI assistant to a real system so it uses that system's actions instead of guessing from a chat. Claude, Cursor and a growing list of clients speak it. m18t runs its own server, so you point your client at your workspace and it works.
Which agent can I use?
Any client that speaks the protocol. This is not built around one vendor. Clients that sign in through the browser need no token at all; clients that want a header take one you issue yourself.
Can my agent see other people's brands?
Only what its person can already reach, and less if you narrowed the token. The two are combined, so the scope only shrinks. A token scoped to no brands reaches nothing.
What stops an agent from wrecking my workspace?
There is no delete action for it to call. What it can do is a fixed list, so nothing arbitrary runs. And you can hand it a token that cannot write at all.
Does it cost me AI tokens?
Reading and writing your workspace calls no model, so it costs nothing beyond what you already pay for your own agent. Features inside m18t that do call a model use your own provider key, billed to you directly.
Is this live, or is it roadmap?
Live and in production. It is the surface this product is built on rather than an integration added to the side, and m18t is run through it daily.
Bring your own agent.
Free while it is in beta. Give yourself a token that cannot write, let your agent look around first, and widen it when you are ready.