● Live · 406 regulated metricsFCA · Basel · NHS · TCFD

The metric standard your AI agents trust.

Regulated metric definitions wired into MCP. Every formula carries its source paragraph, its lineage, and a signed audit trail — so when your agent quotes CET1 ratio, it's the same number the regulator expects.

0+
Regulated metrics
0
UK industries
0
Regulatory sources
0%
Sourced from regulators
Your workspace

Deploy custom metrics alongside the regulatory standard

Define your own metrics in the custom.<org> namespace. They live in your private workspace, resolve over the same API, and never leave your tenant.

01

Define privately

Write metric YAML in the custom.<org>.* namespace. Your definitions are private to your tenant — other users never see them.

02

Resolve over the same API

Custom metrics are served via the same REST and MCP endpoints as regulatory metrics. One integration, both sources.

03

Promote when ready

When a custom metric is battle-tested, export it to the public marketplace for community review and certification.

Example
id: custom.acmebank.treasury.net_interest_margin
title: Net Interest Margin (Internal)
industry: banking
formula:
  dialect: ansi
  sql: |
    SELECT (interest_income - interest_expense)
           / NULLIF(avg_earning_assets, 0) AS nim
    FROM {{treasury_daily}}
    WHERE report_date = :as_of
The problem

Three reasons your AI agent gets the number wrong.

01
Hallucinated definitions

An LLM asked “what’s our gross margin?” will confidently invent the formula. There’s no grounding source.

02
No audit trail

When a board member queries a number, you can’t tell them which dataset, which formula version, or which paragraph of regulation it traces to.

03
Scattered definitions

Three teams, four spreadsheets, six dashboards, all subtly disagreeing on the same KPI. The agent picks one at random.

How it works

Crawl → Extract → Serve → Audit.

Step 01
Crawl regulators

Regulatory source monitoring — starting with CRR, PRA Rulebook, and Basel III. More sources added as industries launch.

Step 02
Extract definitions

LLM-assisted extraction normalises every metric into formula + inputs + outputs + paragraph reference.

Step 03
Serve over MCP

Any MCP-capable client (Claude, Cursor, your gateway) resolves a metric ID to its canonical formula in one call.

Step 04
Audit every read

Hash-chained log of who resolved what, when, against which version. Exportable for regulators.

Coverage

Three industries. One contract.

Banking
152 metrics

Capital, liquidity, credit risk, conduct.

· Basel III · CRR · CRD V
· PRA Rulebook · FCA Handbook
· FINREP · COREP
Healthcare
122 metrics

Outcomes, safety, throughput, quality.

· NHS Digital indicators
· CQC inspection metrics
· ICD-10 · SNOMED CT
ESG
132 metrics

Climate, social, governance disclosures.

· TCFD · ISSB · ESRS
· GRI · SASB
· UK SDR · CSRD
Why MetricRegistry

Eight things you only get here.

  • Paragraph-level regulatory citation
  • Hash-chained audit log
  • Version pinning + diff history
  • Validator marketplace
  • MCP-native resolution
  • SQL canonical form
  • Industry-specific schemas
  • CC BY 4.0 licensing
● Banking● Certified · v3.2
banking.capital.cet1_ratio
CET1 Ratio
# banking.capital.cet1_ratio
id: banking.capital.cet1_ratio
title: CET1 Ratio
version: 3.2.0
formula: |
  {{cet1_capital}} / {{rwa_total}}
source:
  framework: Basel III
  paragraph: CRR Art. 92(1)(a)
  effective: 2026-01-01
unit: percent
frequency: monthly
Validators

Open. Peer-reviewed. Transparent.

Open submission

Anyone with the credentials can submit a metric definition for review. No gatekeeping.

Peer review

Two domain validators sign off before a metric goes from draft to certified.

Transparent reasoning

Every approval and rejection ships with a public reason. The reputation graph is on-chain.

Ready to give your AI agents a single source of truth?

Start with the open tier — no credit card. Wire MCP in three lines.