Help agents navigate data.

MCP-based tools that add context to data workflows, for reliable agent decisions.

retention:7ypii.sensitiveaudit:required
pii.maskedgdpr.consentanonymize:90d
gdpr.art6freshness:15mml.approved
weight:0.95inherits:orders.amountstale_after:5m
no_exportsync.prohibitedaccess:09-17_ET

Reliable decisions for data agents.

Business rules, technical requirements, and organizational knowledge as instructions for agents. Author policies, set conditions, enrich tables, validate uses, and expose that context for agents.

Safe Query Generation
Churn analysis · support + customer data
SELECT *
FROM support_tickets s
JOIN customer_profiles c
ON s.customer_id = c.customer_id
METATATE RUNTIME ANALYSIS
s.message_text
Customer interaction data · restricted
RESTRICTED
c.email
Contains PII · high exposure risk
HIGH RISK
shared_analytics
BI & reporting
APPROVED
Risk: Low · all fields permitted
churn_model_training
ML training pipeline
REQUIRES CHANGE
Unsafe join detected · rewriting query...
customer_targeting
Marketing activation
RESTRICTED
Access blocked · contains restricted data

Context that moves with your data.

A decision-context layer for data agents. Surface the data and context behind a question, capture the judgment the agent should apply, audit and evaluate the decisions made.

Persistent Context

Business logic, data contracts, policies, lineage, access rules, and asset metadata as structured, machine-readable context.

Programmable Rules

Agents evaluate dynamic business rules instead of relying on hardcoded branches or human interpretation.

Versioned & Portable

Context layers are versioned. A policy that changes doesn't break every system relying on it.

Context MCP
Processing queries with instructions
Active instructions:5
Instructions Library
PII protection rules
90-day retention policy
Access tier requirements
Audit trail requirements
Service tier checks
Live Decision Stream
Query Agent
modify
Query: Run retention query
Instruction: Schema contract
Redirected to retention_cohorts
Pipeline Agent
allow
Query: Apply MRR transformation
Instruction: Business rule
Rule set validated
Compliance Agent
deny
Query: Export user records
Instruction: PII policy
Contains unmasked PII

Agents can't operate without context.

Data agents fill gaps with guesses. Those guesses compound across every run.

Agents act on structure, not meaning

A column named revenue means different things in different tables. An agent sees a number. Without context, it can't tell the difference.

analyze revenueassumed

revenue_amount

3 conflicting definitions

proceeding withGAAP bookings

Rules live in the wrong places

Business logic is scattered across threads, wikis, and documents. None of it is readable by an agent.

apply retention filterassumed

retention_policy

No authoritative source

proceeding with90 days

Context disappears at every boundary

The moment data moves across a join, the definition of a field can change. The agent has no way to know.

join datasetsassumed

customer_id

Definition changes across join

proceeding withSource A

No record of why

When an agent produces a wrong result, there is nothing to trace back to. No rule it followed, no decision it logged.

generate reportassumed

output_methodology

No decision log found

proceeding withunknown

What changes when agents have context

The business rules, policies, and procedures an agent needs to act, authored and available to query.

01

Agents query the rules that apply to a workflow

The business logic and requirements are available for an agent to query as it works.

02

Authored once, applied everywhere

A rule authored once holds across every agent, pipeline, and system that touches the data.

03

Reliable decisions where an agent would otherwise guess

With the rules available to query, an agent resolves the situation instead of guessing.