Model Context Protocol Overview

The Ternary MCP server lets an AI assistant answer questions about your technology spend using your live Ternary data. Instead of exporting CSVs and pasting them into a chat, you connect the assistant to Ternary once — after that it can list your tenants, discover your cost dimensions, run cost queries, read your saved reports, review saved reports, check budgets, and explain what changed on a dashboard on its own.

It is built on the Model Context Protocol (MCP), an open standard supported by Claude, ChatGPT, Codex, VS Code, and a growing list of AI tools. Any MCP client that supports remote servers with OAuth can connect.

📘
Setup guides

Connect Claude

Connect ChatGPT/Codex

Connect VS Code

Connect other agents

Server URLs

Use the URL for the region where your Ternary tenant is hosted:

Region	Server URL
US (`my.ternary.app`)	`https://core-api.ternary.app/mcp`
EU (`my.eu.ternary.app`)	`https://core-api.eu.ternary.app/mcp`

Authentication

The server uses OAuth 2.1. When you add the connector, your AI client opens a Ternary sign-in page; you log in with your normal Ternary credentials and grant access. No API keys are involved.

Every tool call runs as you, with exactly the permissions your Ternary user has. The assistant can never see a tenant, report, or cost figure that you could not see yourself in the Ternary UI.

📘
You need an existing Ternary account
The connection does not create accounts. If your email is not already a Ternary user, sign-in fails.

Available tools

All tools are read-only.

Tool	What it does
`ternary_list_tenants`	Lists the tenants (organizations) you can access. Other tools take a `tenantID` from this list.
`ternary_list_dimensions`	Lists the dimensions and measures available for a tenant, so queries use real field names instead of guesses. Supports search and paging.
`ternary_get_dimension_values`	Samples the distinct values a field can take (for example, real service names), so filters use real values.
`ternary_run_cost_query`	Runs a cost/usage query: date range, grouping dimensions, measures, filters, and time precision. Returns the top groups largest-first plus a server-computed summary (exact total for the range, and how much of it the returned rows cover).
`ternary_list_reports`	Lists a tenant's saved cost reports, searchable by name.
`ternary_get_report_data`	Fetches a saved report's rows, one page at a time.
`search`	Finds your tenants and saved reports by name. Exists for clients that require the MCP search/fetch contract (ChatGPT deep research).
`fetch`	Retrieves a `search` result by ID: a tenant summary or a report's data rows.
`ternary_list_budgets`	Displays a tenant's budgets with the figures shown on the Budgets page: amount, spend to date, projected month-end spend, and health status (on track, at risk, over budget, or not yet evaluated). Ordered most severe first, filterable by status.
`ternary_list_dashboards`	Displays a tenant's dashboards with name-based search capability.
`ternary_get_dashboard_definition`	Describes a dashboard's composition: widgets in reading order, each with its type, title, and the report or budget it renders, resolved by name.
`ternary_get_dashboard_delta`	Compares a dashboard across two time windows in a single call, returning per-widget current and prior values, absolute and percent change, and the dimension groups that moved most. Defaults to the last 7 full days against the 7 preceding days.

A typical conversation flows through them in order: pick a tenant → discover fields → sample values → run the query. The assistant does this on its own; you just ask the question ("what did we spend on BigQuery last quarter, by project?").

Current limitations

Read-only. The assistant can query costs and read reports. It cannot create or edit anything in Ternary — no budgets, labels, rules, or reports.
FOCUS billing data only. Queries run against the FOCUS-normalized billing dataset (FOCUS_BILLING). Other data sources (Kubernetes, carbon footprint, custom datasets) are not exposed yet.
Current product coverage: Cost queries, saved reports, budgets, and dashboards are exposed. Anomalies, recommendations, forecasts, and commitment data are not.
Budget figures are a snapshot: Budgets are monthly and each carries the figures from its last evaluation, so the reported period can predate the current month. No month-by-month history is available.
Dashboard comparison covers report widgets: Up to 15 report widgets are compared per call, with any skipped widgets disclosed. A widget that cannot be compared honestly returns the reason instead of a figure: variance reports, non-summable measures such as averages and maximums, and widgets whose data could not be read. Budget widgets pass their evaluated status through unchanged.
Invoice-month reports compare on usage dates: A report that normally accrues by invoice month is compared over a plain usage-timestamp window, so its figures are not on the report's own accrual basis. The affected widget states this.

Data protection

Transport is HTTPS only, authenticated with short-lived OAuth tokens scoped specifically to the MCP endpoint.
Every tool call is permission-checked through the same authorization layer as the Ternary web app and logged for audit.
Ternary never sends your data anywhere on its own — data moves only when your AI client calls a tool during your conversation. What the AI provider then does with conversation content is governed by your agreement with that provider (Anthropic, OpenAI, etc.).