Model Context Protocol

Your CRM and Brain, inside your AI assistant

SAGARIS serves a Model Context Protocol endpoint at /api/v1/mcp. Point any MCP client at it with your workspace API key and your assistant reads your CRM and Brain. Reads only, so nothing can change.

The endpoint is running today. This page lists the tools it offers, shows how your API key decides what each one can reach, and gets you connected in a few minutes. Ask your assistant about a deal and the answer comes from the record.

Your assistant reads the real record

Model Context Protocol is an open standard. It hands an AI client a set of tools it can call. SAGARIS runs the server half at /api/v1/mcp, over Streamable HTTP in stateless JSON mode. That means one JSON-RPC message per POST, one JSON response back, and no session to open or close. Connecting a client is one short piece of configuration: the endpoint URL and your API key.

So the assistant your team already works in can ask your workspace a question and get the answer from the record itself. No more pasting a stale export into a chat window and hoping it is current. Your pipeline stays where it lives, and your people read it where they already work.

Your revenue data becomes something the assistant can call, not something a person has to go and look up.

Safe to connect on day one

You can hand this endpoint to an assistant without wondering what it might change. Read only here is built into the code, not promised in a sentence. The tool list is derived from the public API and filtered to GET, so a write operation can never turn up as a tool, whatever gets added to the API later. Nobody has to remember to keep it that way.

Every tool also tells the client it is read only and non-destructive. Good clients use that signal to answer your question straight away instead of stopping to ask you for permission first.

An assistant connected to SAGARIS tells you what is true right now. Sending, dialling and enrolling stay with your team.

You decide what each key can see

It uses the workspace API key you already create in settings, sent as a bearer token. Three things follow, and all three are enforced in code rather than written in a policy:

  • The key names the workspace. A client never gets to pick one, so it only ever reaches yours.
  • Scopes filter the tool list before the client sees it. A tool your key does not cover is never offered at all. That is the version an assistant handles cleanly.
  • Every message needs a valid key, the opening handshake included. There is no step where the server talks to a stranger.

Requests are rate limited per key, and a browser client has its origin checked before anything else happens. Revoke the key in settings and the access ends. That is the part you want on the day somebody leaves the team.

You choose what leaves the workspace

The Brain holds more kinds of record than this endpoint hands out, and every one of those calls was made on purpose. Internal delivery commitments, the record of what your own team promised a customer, stay inside the workspace. So does machine-derived competitor intelligence, which only reads properly next to its source and its date. Your most sensitive context stays where you can see who touched it.

The list of subject types this endpoint can read is compiled from the same table the runtime check uses. So this page and the product cannot drift apart. Add a new kind of subject and the build stops until someone decides, on purpose, whether an outside client should see it.

Included in your seat

Nothing beyond the seat. SAGARIS is $499 per seat per month on the founding price, every module and every agent included, with no seat minimum. The endpoint ships with the product rather than in a tier above it, and tool calls are not metered.

The tool surface

What your assistant can ask for.

These are the tools the endpoint offers today, with the scope each one needs. You control the scopes, so a key only ever sees the tools you granted it.

sagaris_list_contactsrequires contacts.read

Your workspace contacts, through the same route and the same pagination the public API serves. The assistant sees exactly what a key holder sees, so the answer matches the screen.

sagaris_list_sequencesrequires sequences.read

Your outbound sequences, so you can ask what a contact is enrolled in right now and get a straight answer.

sagaris_brain_claims_currentrequires contacts.read

What your workspace believes right now about one contact, account or opportunity. Best-rank claims only, with facts known to be wrong left out and counted so you can see the number. Reach for this one when you need what is true today.

sagaris_brain_contact_dossierrequires contacts.read

Every claim on record about one subject, each with its confidence, when it was seen, and a pointer to the evidence behind it. Ask as of a past date and you get the answer as it stood that day.

sagaris_brain_nba_featuresrequires contacts.read

One flat record of the signals a next-best-action decision runs on: renewal window, buying-intent stage, budget approval, competitor activity, open objections, and which facts are contested. It answers as of a past date too.

Every one of them reads. Nothing here writes, so you can wire it up once and leave it running.

FAQ

The questions this endpoint gets asked.

Short answers, including the ones about what it will not do. Every one of them describes behaviour that is running today.

What is the SAGARIS MCP endpoint?

A Model Context Protocol server at /api/v1/mcp that lets an AI client read your SAGARIS workspace. It speaks the Streamable HTTP transport in stateless JSON mode, one JSON-RPC message per POST, and it authenticates with your workspace API key as a bearer token.

Can an assistant change anything in my workspace through it?

It reads, and only reads. The tool list is derived from the read operations of the public API, so a write operation cannot appear as a tool at all. Every tool is marked read only and non-destructive to the client. Sending, dialing, enrolling and editing are not reachable from this endpoint. You can hand an assistant your pipeline without handing it your outbox.

What can it read?

Your contacts and your sequences, and three Brain views over a contact, account or opportunity: what the workspace currently believes, the full dossier of asserted claims with their evidence, and the flat feature record behind a next-best-action. The Brain views also answer as of a past date.

How does it know which workspace to read?

From the key. The workspace is resolved from the API key itself and a client cannot pass one, so it cannot reach a workspace the key does not belong to. Scopes then filter the tool list before the client ever sees it, and every message needs a valid key including the opening handshake.

Which clients can connect to it?

Any MCP client that speaks the Streamable HTTP transport and lets you set a bearer token. Connecting is a matter of pasting your workspace API key into that field, so there is no install and no sign-in flow to sit through. Tell us which client your team uses and we will check it for you.

What does it cost?

It is included in the seat. SAGARIS is $499 per seat per month on the founding price, with every module and every agent in it and no seat minimum. There is no per-call charge and no higher tier gating the endpoint, so your team can wire it into whatever assistant they already use.

How do I turn it off?

Revoke the API key in workspace settings. Access ends with the key, because the key is the only credential the endpoint accepts.

It is already included in your seat.

Once your workspace is set up, create an API key in settings and point your client at it. Your assistant reads live records in minutes. The platform page shows everything it can reach.

Book a demo