Introduction

Polytomic Harbors: governed data, context, and action environments for your AI agents

About

Polytomic Harbors are governed data, context, and action environments for your AI agents. They allow your agents to quickly and securely query data from across all your systems (databases, data warehouses, CRMs, marketing and ad platforms, support tools, spreadhsheets, finance systems, etc) as well as optionally write back to any of these systems in a governed fashion.

Each Harbor consists of these components:

  1. A storage container designed for fast queries. Typically this will be Polytomic-managed storage, though it can also be your data warehouse or other database. Polytomic is agnostic about where the data actually sits.
  2. Syncs that feed the Harbor with tables and fields of your choosing (these can come from anywhere: your data warehouse, production databases, CRMs, spreadsheets, marketing and finance apps, etc). Harbors are scalable to big data (e.g. billions of records).
  3. Context documents that describe the datasets in the Harbor and any business logic specific to your data.
  4. A unique MCP server that agents can use to connect to it and issue queries.
  5. An access control list of authorized users and agents that are allowed to connect to the Harbor.
  6. Optional: Governed action policies for writing to external systems (e.g. CRMs). If, in addition to querying the data in the Harbor, you also want to update data in other systems (e.g. Salesforce), you can specify exactly which fields in these external systems connecting agents are allowed to write to.

Once a Harbor is active, AI agents can connect to it through a unique MCP server or unique API keys, then query the data in natural language. Because of the context documents in Step 3, all connecting agents become automatically aware of how to query the data with accuracy.

Connecting agents

Polytomic Harbors are neutral about the actual agent used to query them. Because they each come with an MCP server, you can use any agent that supports MCP to query your Harbors: Claude, ChatGPT, Notion Agents, and others.

Benefits

The typical approach to providing AI agents with query ability is to give them access to the data warehouse and/or vendor MCP servers. However, especially since most of agent use comes from those outside the data team, there are risks that Harbor mitigates:

1. Joining data across MCP servers is often expensive and impractical

MCP servers are designed for single-provider use. Joining data across multiple systems (e.g. Salesforce, Gong, HubSpot, Snowflake, etc) is often going to fail due to rate-limit exhaustion. In addition, it's a slow operation and expensive token-wise.

It's much faster and cheaper to index the data in Harbor first then query that.

2. Giving an agent access to the whole data warehouse is unsafe

Those outside the data team typically do not need access to all tables in the warehouse. A marketing person may only need three tables from Salesforce and HubSpot. A finance person may only need to query two tables in NetSuite, a Google Sheet, and a table in the data warehouse.

Giving these agents access to the whole data warehouse risks sensitive data being unnecessarily surfaced in response to agent queries.

Harbors, on the other hand, are kept in sync with exactly the source tables and fields specified and no more. Security is solved by physical isolation: it is impossible for an agent to see data outside the Harbor it has access to.

3. Context documents result in accurate query responses

Once you attach context documents (think of them as agent skills specific to the Harbor) to your Harbor, every connecting agent will be automatically aware of them. And because each Harbor's data is curated, unlike with data warehouses there is no risk of your agent being misled by stale and expired tables that should be ignored.

These facts combine to result in fast and accurate responses to agent queries.

4. Per-Harbor user access management

Besides the physical separation of data granted by Harbors, each Harbor comes with its own user and agent-management controls. You have full control over which users' MCP connections have access to each Harbor.

(In the rare case where you do have per-user RBAC permissions set in your data warehouse for every agent access across your organization, Polytomic Harbor can use those permissions to your warehouse for querying rather than managing its own storage indexes.)

5. Harbor management supported through MCP and API

Polytomic has a first-class API for managing Harbors and their context documents (example API here: https://apidocs.polytomic.com/api-reference/harbors/create-context).

This means that, besides clicking in the admin console, you are also able to manage all Harbor provisioning, syncing, and context management through your agents (using the Polytomic MCP server) or through the API. This makes Harbors suitable data stores for customer-facing functionality, as multi-tenant isolation is supported by definition due to each Harbor being isolated from the rest.

6. Governed write actions to external systems

A valid fear when instructing agents to update external systems (e.g. Salesforce) is permission violation. Will the agent accidentally update a field it's not supposed to? This is what Polytomic's governed actions are designed to stop: you can define a policy guaranteeing exactly what objects and fields agents are allowed to update in any system.

Concepts

The subsequent pages in this section cover Harbor capabilities in detail.