MCP-delivered · free for individuals
Everyone's context — not someone's catalog.
Stop re-explaining your data to your AI every session. Connect Claude Code, Cursor, Codex, or claude.ai in one command — your agent recalls your context before it writes SQL. Mismatches surface as a caveat so you and your agent know what to trust.
Works inside the coding agents you already use. Claude Code · Cursor · Codex · claude.ai
The problem is measured — by the labs themselves
21% → 95%+
Analytics-agent accuracy before and after structured, checked context — “a context and verification problem, not code generation.”
Anthropic · 2026
95% → 65%
The same accuracy one month later, without maintenance. Context rots — something has to keep checking it.
Anthropic · 2026
< 1 pt
The gain from retrieval over their entire SQL corpus. More docs don't help — checked structure does.
Anthropic · 2026
Our own numbers, kept separate: in a pre-registered internal paired eval, the same agent scored 36/38 data questions with ClariLayer vs 26/38 without — and on the cheaper model, cost per correct answer flipped to $0.054 vs $0.081. The layer doesn't cost you money; skipping it does.
Also measured elsewhere — Gartner (2026): 60% of agentic-analytics projects relying on MCP alone will fail without a consistent semantic layer. dbt (2026): raw text-to-SQL reaches 64.5% — and fails silently.
Bootstraps SQL · dbt · CLAUDE.md · dictionaries · semantic models
See it work inside the agent
One command to connect. Then your agent recalls the definition you saved, runs the query with its own warehouse access, and reconcile flags what to treat with care.
saved context · returned by recall
Reenactment of the real loop — the same recall → reconcile → caveat flow the MCP runs today. Your agent keeps its own warehouse access; ClariLayer never holds your warehouse credentials and never runs SQL server-side.
New chat, new context window — and your agent has forgotten which table is the real one, how the joins go, and which definition you actually use. You re-explain it. Again.
Hand-typing your definitions into a notes file has the same trust problem as the original numbers: nothing checked it against your warehouse. It drifts, and your agent trusts it anyway.
Wrong table, wrong join, refunds counted in revenue, an active customer defined three different ways — the same mistakes, session after session, because nothing remembers the correction you already made.
01 · The problem
Claude memory, ChatGPT memory, mem0, a CLAUDE.md: they store. None of them can tell you the revenue definition is stale. Each one is a silo. A notes file has the same trust problem as the original numbers.
02 · Bootstrap
SQL, dbt, CLAUDE.md, a data dictionary, or a semantic model. The agent passes the content. ClariLayer feeds on your files, never your warehouse data. No blank-slate wiki.
03 · Recall, then reconcile
Dashboard $1.42M. Agent query $1.51M. $90K gap, QBR in an hour. Reconcile compares the saved definition to the live result shape and records a caveat — not a ruling on which dollar is right.
04 · Remember
The missing refunds join becomes a saved rule: asserted, from you. Standing instructions ship with the connection, so the agent recalls before it writes SQL. The layer compounds.
1 / 4
// Claude memory, this session
remembered: “use fct_orders for revenue”
status: stored
checked against warehouse: never
portable to Cursor / Codex: no
nothing here can tell you the rule is stale.
day-1 context. not a cold empty store.
Dashboard
$1.42M
Agent query
$1.51M
declared net_revenue expected a refunds join.
live result did not have it. $90K gap.
Caveat
> How many active customers?
recall → Active customer · mrr > 0 · asserted
agent runs saved SQL with its own access
remember · you · asserted
“net revenue must net refunds”
next session starts from this, not from zero
Your context layer
Active customer
Definition · you → reconciled
Net revenue (excl. refunds)
Definition · from dbt
orders.region — null before 2023
Schema note · you → reconciled
fct_orders ↔ dim_customers join
Join path · you
Reconciled against your source — not blindly asserted.
The enemy is unchecked memory
They store. They do not reconcile. Each platform is a silo. Even mem0 shipped additive-only. A CLAUDE.md is asserted text with the same trust problem as the original numbers.
One portable layer across Claude Code, Cursor, Codex, and claude.ai. Bootstrap from files you have. Reconcile against warehouse samples or row-free HubSpot evidence. Mismatch → caveat. Otherwise it stays asserted. Those are the only live statuses.
Without your saved context, the agent guesses from raw table names. With it, the agent recalls the definition you reconciled against your warehouse — and knows what to treat with care.
The first reconcile
The acute analyst moment: two sources disagree and the QBR is in an hour. ClariLayer reconciles a saved definition against your real warehouse result and flags the drift as a caveat — checked against source, never blindly asserted.
Your dashboard says
$1.42M
Net revenue for the quarter — the number on the board.
Your agent’s query returns
$1.51M
The ad-hoc query your agent just wrote, against the same warehouse.
A $90K gap, and no way to tell which one is right.
reconcile
Your agent runs the stored net_revenue SQL with its own access and reports the result shape back. ClariLayer compares the saved definition’s declared signals — its columns, grouping, and aggregates — against what came back.
They don’t line up: the live result is missing a column the saved definition expects, so reconcile records a caveat. That’s the signal to look closer — not a ruling on which dollar figure is right.
The caveat sends your agent digging
With its own warehouse access it traces the $90K to the cause: the ad-hoc query never joined the refunds table, so it reported gross, not net. You ship the refund-adjusted $1.42M.
remember
You correct it once so next quarter the agent starts from it instead of rediscovering it:
The caveat caught the $90K discrepancy an hour before the QBR. Your agent traced it to the missing refunds join, you shipped the right number, and the correction is remembered for good. Your agent runs the query with its own access; ClariLayer never holds your warehouse credentials and never runs SQL server-side.
Live now · HubSpot CRM reconcile
Save a row-free contract for a HubSpot property — expected stages, a canonical value, deprecated aliases, or an expected label. Your agent reads HubSpot with its own authorized access and sends ClariLayer only bounded property metadata and value distributions.
On this personal path, ClariLayer never receives CRM credentials or records, and it never calls HubSpot. A mismatch becomes a caveat; otherwise the contract remains asserted. Salesforce contracts can be stored and recalled, but Salesforce reconciliation is not enabled.
Hand-run check · a design partner's live HubSpot
The obvious queries
What reconcile surfaced
Hand-run with the partner's agent using its own access — bounded, row-free evidence only. The rules your CRM enforces are not the rules your team believes. Reconcile is how you find out before the QBR does.
One analyst, your own data, your own agent. No governance rollout or procurement cycle — just your context, bootstrapped, reconciled, and remembered.
Bootstrap
Your agent doesn't start from zero — and it doesn't start from a hand-typed CLAUDE.md. Point ClariLayer at the work you already have.
What gets ingested
“Bootstrap my context from ./analytics/sql + my dbt models.” Real working context on the first session.
Reconcile
A saved definition is reconciled against a warehouse result or bounded, row-free HubSpot evidence collected by your agent.
What reconcile returns
Warehouse access and CRM access stay with your agent. ClariLayer compares only the supported evidence it sends.
Remember
Every correction, every reconcile, every new note persists. Your agent grounds on more of your context over time.
The retention loop
“In normal use, we ask vague follow-up questions and expect ClariLayer to prevent us from re-explaining established business rules.” — SIRAYA, RevOps design partner. The context you build is the moat.
Governed Context Edge · private pilot
It does not average. Yours free, forever. The team product promotes what you reconciled into a shared canon: propose up, adopt down with agency, never a silent overwrite. Built, hand-run with design partners. No public price.
Personal layers sit at the bottom, a team layer in the middle, and org canon at the top. Governed Context Edges between them carry propose-up and adopt-down. When two personal numbers conflict, the Edge adjudicates; it does not average or silently overwrite.
Layers stay yours
Individuals, then team, then org canon. The layer is free; the Edge between layers is governed.Flow both ways
Propose up what you reconciled. Adopt canon down with agency. Never a silent overwrite.The Edge adjudicates
When two people's numbers conflict, a human decides what enters canon. It does not average.For teams · private pilot
ClariLayer starts as your personal context layer. The Governed Context Edge — your reconciled definitions promoted into a governed team canon, with ownership, approval, and one right metric — is built and in private pilot. A few design-partner slots are open.
The definitions and corrections you build solo are exactly what later merges into shared, owned team context — the same engine, one level up.
When two people's numbers conflict, the Edge surfaces it and a human settles it. Context proposes up and adopts down with agency — never a silent overwrite. One right answer, owned and approved, for everyone's agents.
Start as your personal context layer with no procurement. When the team is ready, the Edge is already built and running in private pilot — design-partner slots are hand-onboarded, and a few are open now.
Connect your AI
Connect Claude Code, Cursor, or Codex with a context key, or add ClariLayer as a custom claude.ai Connector and approve over OAuth. Managed instructions keep supported local agents on the recall, confirmed-update, and completion-checkpoint loop.
Add ClariLayer as a custom Connector, paste only the MCP URL, then sign in and approve in your browser.
https://app.clarilayer.com/api/mcp/mcpClaude Code, Cursor, and Codex authenticate with the context key you mint in ClariLayer.
Run in your terminal
claude mcp add --transport http clarilayer https://app.clarilayer.com/api/mcp/mcp --header "Authorization: Bearer cl_YOUR_CONTEXT_KEY"Replace cl_YOUR_CONTEXT_KEY with your context key. The key is shown once at creation, so paste it straight into the command.
Built to be trusted with your data
The whole point is that your AI's context is grounded against reality, not just asserted. We measured what that is worth — and we label every claim with exactly how far it goes.
Measured, not manufactured
In our internal paired eval, the same agent answered 36 of 38 data questions correctly with ClariLayer connected — 26 of 38 without. On the cheaper model, cost per correct answer flipped: $0.054 with the layer vs $0.081 without. And under session load, the control went confidently wrong; the ClariLayer arm did not.
Shipped, not slideware
Bootstrap, recall, remember, and reconcile are live in production, alongside review, lifecycle, full-entry fetch, and a durable completion receipt. Connect Claude Code, Cursor, or Codex with a context key, or claude.ai over OAuth.
A standard, not a shortcut
We built the stronger “verified” stamp, ran eight adversarial review rounds against it, and refused to ship it — one false “verified” is the failure a trust product cannot survive. Every mark says asserted or caveat — reconcile checks a definition against a warehouse result or bounded, row-free HubSpot evidence, and a mismatch becomes a caveat. That refusal is the product.
Your data, your access
On the personal MCP path, ClariLayer never runs SQL or calls HubSpot. Warehouse evidence can include optional preview rows; HubSpot evidence contains only bounded metadata and aggregate distributions, with CRM rows forbidden.
FAQ
What ClariLayer can see, what it doesn't touch, what's free, and what “reconciled” actually means.
Connect ClariLayer to Claude Code, Cursor, or Codex in one command. Free to start — no team, no procurement, just your context.
Connect your AIFor teams
The Governed Context Edge is in private pilot — a shared, governed canon for your whole team's agents. We onboard design partners personally.
We use privacy-friendly analytics
With your consent we use PostHog and Vercel Analytics to understand how ClariLayer is used so we can improve it. We never sell your data. Errors are always monitored (without analytics) so we can keep the app reliable. You can change your mind anytime.