Atlas Agent

MCP server architecture

See how Atlas binds MCP tool calls to workspaces, roles, and tracker budgets so every artifact is provable.

Diagram

MCP Architecture

Visual map of MCP clients, protocol, servers, and exposed tools.

MCP Client

MCP protocol

MCP Servers

Client apps

  • Chatbots
  • Agents
  • Humanoid robots
  • Other clients

Connected tools

  • Google Drive
  • HubSpot
  • Gmail
  • Other tools

MCP server exposes tools such as

Upload file
Send email
Generate sales comps
Generate rental comps
Other actions

Atlas uses a layered architecture: Owner, Workspace, Transactions, Items, Files. Each layer carries workspace_id so we can filter every query before we even touch the MCP tool code. This keeps multi-tenant brokers safe while still letting them publish a single MCP server URL.

Workspace-first filtering

Every request starts with workspace validation. The MCP server verifies the workspace_id, role, and consent scopes before it even inspects tool parameters. This preserves the “deny by default” rule documented in the Knowledge Base.

Once the workspace is verified, the server checks whether the actor is Owner/Admin (full access) or invited Client (transaction-scoped access). The policy engine rejects any attempt to cross workspaces.

  • All objects carry workspace_id
  • Every query filters by workspace_id first
  • Never let a Client select across workspaces

Transaction, Item, and File lineage

Transactions collect every workflow for a given deal. Items represent tasks, forms, and documents. Files are the signed PDFs, comps, and reports. MCP tools always log which transaction/item/file they touched so you can answer “Who generated this PDF?” instantly.

Atlas provenance tags combine workspace_id, transaction_id, tool_name, and event_id. You can feed those tags into downstream RAG systems or audit exports.

Owner/Admin: see everything. Clients: stay inside invited transactions. All objects carry workspace_id.

Policy + tracker loop

The tracker & guard store maintains counters per office, user, tool, vendor, and time window. Before a tool executes, MCP calls the preflight service to ensure budgets are available and consent scopes still apply.

After execution, the postflight service writes a signed usage event with the fields listed in the Knowledge Base. This closes the loop and feeds alerts, dashboards, and billing.

  • limits by office
  • user
  • tool
  • vendor
  • model
  • time window

Deploy pattern

Most teams host the MCP server inside Atlas, then run thin clients in Custom GPT, Slack, or Playwright. Advanced teams fork the server, keep our tracker services, and extend the tool catalog with brokerage-specific flows.

  • Stand up an Atlas Server Builder environment or fork the repo.
  • Declare each tool contract: inputs, outputs, scopes, rate caps, latency, and pricing.
  • Attach tracker policies, identity roles, and consent scopes so every call is audited.
  • Expose the server URL to Custom GPTs, Slack apps, VS Code, or any other MCP client.

Atlas Agent

Run your own MCP server

Use Atlas Server Builder to launch faster, then upgrade to Hosted Atlas Bot when you need more seats and surfaces.

Related guides

What is an MCP server?

Pillar primer on Atlas Agent MCP strategy.

Go to What is an MCP server?

Knowledge Base

Identity, consent, provenance, tracker guard details.

Go to Knowledge Base

Pricing

Compare Server Builder, Starter Kits, and Hosted Atlas Bot.

Go to Pricing
Atlas Agent