MCP trust layer for metric agents

AI infrastructure for autonomous data and metric agents.

Your AI keeps forgetting the metric logic your team already approved.

ChatData saves the approved definition, source, caveats, proof receipt, and rerun path for recurring KPI questions, then gives Claude Code, Cursor, and Codex the same trusted route next week.

Free for 7 days. Decide what to keep, expand, or stop on a day-7 live call.

Install contract
ChatData · Live proof loop
Recurring questionWhy did self-serve conversion drop last week?
ChatData trust gate4 checks passed
Approved metricSelf-serve conversion v3
Source tied outSQL + Growth dashboard within 0.2 pp
Caveat flaggedCampaign tagging changed
Reusable routeSame path on the next MCP pull
Answer stateApproved and safe to reuse
See how proof works →

The recurring metric loop

The answer exists. The next run still starts over.

Teams keep metric truth in Notion, dbt catalog pages, dashboard screenshots, shared Sheets, and analyst memory. Claude, Cursor, and Codex can answer fast, but the number is not worth sharing until they use the reviewed route.

Metric truth is scattered

The definition lives in one place, the SQL lives in another, and the dashboard owner remembers the caveat. Claude sees the metric name and fills in the rest.

Proof is hard to repeat

A dashboard screenshot helps today. A dbt model helps if the agent can read it. Neither helps next week unless the source, freshness, caveat, and validation rule are saved together.

Fixes don’t compound

You correct the same answer in the thread, deck, or notebook. Nothing carries into the next Claude, Cursor, or Codex run, so the team pays the same cleanup cost again.

How it works

Six checks run before a saved answer can be reused.

Existing data catalogs were built for humans to browse. ChatData gives Claude Code, Cursor, and Codex the reviewed route for one metric answer: definition, source, freshness, caveat, validation, and proof.

Under the hood, ChatData can store metric definitions using the open Open Semantic Interchange core spec.

1

Right metric definition?

Resolves against your governed metric registry, not what the agent guessed from the schema.

Metric trust
2

Source trusted and fresh?

Checks the approved source and last-refreshed timestamp before any answer is formed.

Freshness
3

Frame stated and tested?

Names the explanatory frame, what supports it, and what would break it before committing.

Frame
4

Data passed quality checks?

Uses saved validation rules, expected ranges, and source tie-outs before drawing conclusions.

Validation
5

Caveats visible?

Known exceptions, lags, and schema quirks are attached from saved context.

Caveats
6

Rerun works next time?

After review, MCP pulls the saved route again. Invite only after the rerun uses the same metric, source, caveat, and proof.

Answer path
Without ChatData
Claude answers confidently

Wrong grain. No caveat. Sounds right.

Data scientist reopens the stack

Notion, dbt, Sheets, dashboard screenshot, old thread.

Cleanup loop begins

Recalculate, add caveats, re-share.

Same question next week

Nothing was saved. Repeat.

With ChatData
Resolves the right metric

Governed definition, approved source, correct grain.

Attaches saved caveats

iOS lag, schema note, freshness — pulled from saved context.

Rerun is ready to share

Source, caveat, proof receipt, and validation path are visible.

Path saved for next time

Next MCP pull starts from the reviewed route.

Trial access

Bring one metric question your team keeps re-answering.

Start with a dashboard screenshot, dashboard URL, GitHub SQL/dbt link, metric definition, or source doc. No card. Trial access opens after work-email verification.

Include the messy context: conflicting metrics, uneven source quality, alternate explanations, skeptical stakeholders, or a weekly review that needs the same answer again.

Company context will use your email domain. Context id: ChatData-your-domain.

By starting the trial, you allow ChatData to sync analytics metadata: SQL patterns, metric definitions, answer paths, and caveats. ChatData is metadata-only by design and blocks obvious secrets and raw-row patterns before writes are accepted.

No card. Verify your work email before company context opens.