Skip to main content

One Snowflake MCP endpoint for Claude, ChatGPT, and Gemini Enterprise.

Serve Claude, ChatGPT, and Gemini from a single JSON-RPC endpoint backed by Snowflake views, without exposing source credentials to client models.

Why Model Context Protocol (MCP)

AI models need live operational context to produce accurate, defensible work. Connecting enterprise systems to them has typically meant bespoke API wrappers, hand-built prompt pipelines, or unmonitored database exports.

Customer Zero uses the open Model Context Protocol (MCP), a JSON-RPC interface through which models discover tools, inspect schemas, and query resources. With Snowflake behind an MCP gateway, models query structured tables through token-authenticated views with logged permissions.

Governance boundaries & grant model

Instance-scoped grants
Consumer user × Source instance × Client

A query cannot cross a source boundary without an explicit, active grant record. Each grant names the consumer user, the exact source instance, and the authorised AI client runtime.

Credential isolation
No plaintext secrets in MCP context

Source credentials sit in Google Secret Manager as opaque resource pointers. The MCP gateway runs queries against Snowflake views, so clients never see or receive source tokens.

Immutable audit trail
Append-only audit events

Every MCP query, authorisation check, grant creation, and revocation emits an immutable audit event. Operators can review the full authorisation history through GET /audit-events.

Connect Claude, ChatGPT, or Gemini Enterprise

One MCP gateway serves every supported client. Operators provision a single MCP URL with token-based access, and each team uses the model runtime it prefers. The URL and token are issued after sign-in.

  • Claude logoClaude
  • ChatGPT logoChatGPT
  • Gemini Enterprise logoGemini Enterprise
  1. Claude

    1. Open Settings, then Connectors, and choose Add custom connector.
    2. Paste your organisation's MCP server URL from the Customer Zero dashboard.
    3. Authorise with the access token issued to your consumer user.
  2. ChatGPT Enterprise

    1. In workspace settings, enable developer mode and add a custom MCP connector.
    2. Enter the MCP server URL and choose token-based authentication.
    3. Paste the access token, then enable the connector in a chat.
  3. Gemini Enterprise

    1. In the admin console, register a new MCP data source for your organisation.
    2. Provide the MCP server URL and the access token as the credential.
    3. Assign the data source to the teams that hold a matching grant.

Supported source catalogue & ingestion status

Ten business systems have a connection path into the Snowflake schema. Xero is connect-only for now, and Quinos POS and Raptor POS are in beta.

Supported sources, how each connects, the Meltano tap, GCS landing and Snowflake models behind it, and how it is represented in Snowflake
SourceConnection modelLanding and modelsSnowflake schema representation
Google AdsSelf-serve OAuthMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsCampaign, ad group, keyword, search-term, and spend tables
Meta AdsSelf-serve OAuthMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsAd account, campaign, ad set, and custom audience spend tables
Google Analytics 4Self-serve OAuthMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsTraffic acquisition, event counts, page views, and conversion tables
Google Search ConsoleSelf-serve OAuthMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsSearch performance data for each verified site property
ShopifySelf-serve API tokenMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsStore data from the Shopify GraphQL Admin API, one store per instance
ClockifySelf-serve API keyMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsTime entries, project allocations, billable rates, and member activity
Google Business ProfileOperator-provisionedMeltano tap, GCS JSONL, c0_raw_feeds then c0_analyticsPer-location search impressions, review sentiment, and ratings
Quinos POSOperator-provisioned agent (beta)On-premise agent, GCS landing, c0_raw_feedsOn-premise point-of-sale line items, transactions, and tender types
Raptor POSOperator-provisioned agent (beta)Site-installed agent, GCS landingPoint-of-sale sales data from the site's Raptor server
XeroConnect-only setupNone: no ingestion workflow runsAccounting setup available; ingestion workflow not currently active

Knowledge Harness & operational context

Numbers without context get misread. A 20% decline in marketing spend can look like a performance problem unless the model knows a seasonal promotion has ended.

The Customer Zero Knowledge Harness pairs quantitative Snowflake tables with qualitative operational documents: markdown playbooks, brand voice rules, campaign guidelines, and audience definitions. When an AI client queries the MCP endpoint, the Knowledge Harness returns the relevant business context alongside the metric rows, so answers reflect how the business operates.

Hosting and operations

Operator
IKMJ (Ikigai & Majime Pty Ltd)

An active Australian private company that builds and operates Customer Zero. ikigaimajime.com.au

Hosting
Google Cloud Platform, Melbourne, Victoria

The entire production MCP stack runs in this region. Ingestion pipelines, credential references, and Snowflake endpoints all run in Australia, with no cross-region replication.

Certification
None asserted

Customer Zero does not currently hold SOC 2, ISO 27001, or IRAP certification.

Technical teams can check the security controls and data handling on the Security & Trust page or request architecture documentation at sales@customerzero.app.

Provision an MCP endpoint for your team.