ClariLayer

Stop re-explaining your data to your AI every session.

The individual-analyst context layer, delivered over MCP.
Connect it to Claude Code, Cursor, Codex, or claude.ai — your agent stops making the same data mistakes.

Website · Docs · Get started (free) · Use cases

ClariLayer is an individual-analyst context layer, delivered over MCP. Connect it to Claude Code, Cursor, Codex, or claude.ai and it bootstraps your real working context from the SQL and dbt you already have, reconciles your definitions against your warehouse, and remembers your corrections — so your agent stops re-explaining your data and stops making the same mistakes every session.

_{A seeded demo warehouse: your agent recalls a saved definition, reconciles it against real results, and the mismatch is flagged as a caveat that's waiting next session. Statuses are asserted / caveat — never "verified".}

The problem

Every new session, your AI coding agent starts from zero about your data. So it makes the same mistakes — queries the wrong table, picks the wrong join, counts refunds in revenue, uses a churn definition you deprecated months ago. You correct it. Next session, it forgets, and you correct it again.

A hand-written CLAUDE.md of definitions helps a little — but it has the same trust problem as the original numbers: it's just asserted text. Nobody checked it against your warehouse.

What ClariLayer does

It gives your agent a durable, reconciled memory of your data context — and it lives inside the agent you already use, over MCP. Four verbs, all live:

The context you build compounds across sessions and is portable across Claude Code, Cursor, Codex, and claude.ai.

These four verbs are the in-flow core loop. The full contract today is 19 MCP tools at capability v51 (the four above plus propose / propose_batch, the entry and reasoning lifecycle, supersede, the read-only suggest_links, get_context_entry for an entry's full stored content, get_project_stanza, the completion-receipt context_checkpoint, capabilities, and a health check). The canonical, live list is always discoverable by your client at connect — via the initialize response or a capabilities call — so you never have to trust a doc over the wire. See CAPABILITIES.md for what each recent capability bump added.

Install

Fastest — one command. Auto-detects Claude Code, Cursor, and Codex, writes the right config, and offers to add the standing-orders block to your CLAUDE.md:

npx clarilayer init

You'll need a free context key — sign up at clarilayer.com, then open Connect your AI to mint one. The CLI prompts for it and validates it. Full options: CLI.md.

claude mcp add --transport http clarilayer https://clarilayer.com/api/mcp/mcp --header "Authorization: Bearer cl_YOUR_CONTEXT_KEY"

{
  "mcpServers": {
    "clarilayer": {
      "url": "https://clarilayer.com/api/mcp/mcp",
      "headers": { "Authorization": "Bearer cl_YOUR_CONTEXT_KEY" }
    }
  }
}

[mcp_servers.clarilayer]
url = "https://clarilayer.com/api/mcp/mcp"
http_headers = { "Authorization" = "Bearer cl_YOUR_CONTEXT_KEY" }

[mcp_servers.clarilayer]
command = "npx"
args = ["-y", "mcp-remote", "https://clarilayer.com/api/mcp/mcp", "--header", "Authorization: Bearer cl_YOUR_CONTEXT_KEY"]

On claude.ai? No context key needed — claude.ai connects over OAuth instead. Open Settings → Connectors → Add custom connector, paste https://clarilayer.com/api/mcp/mcp, then sign in and approve when prompted. There is no cl_… key on this path.

See QUICKSTART.md for the full walkthrough and troubleshooting.

Then tell your agent to actually use it

Paste this into your project's CLAUDE.md (or AGENTS.md) so your agent reaches for ClariLayer proactively instead of waiting to be asked. The same stanza, as a ready-to-paste file, is examples/CLAUDE.md:

## ClariLayer — your data context layer (use it proactively)

ClariLayer is connected over MCP and holds this project's durable data and engineering context: definitions, schema notes, reusable SQL, assumptions, caveats, decisions, and the engineering decisions, constraints, and incident lessons this repository relies on. Use it WITHOUT waiting to be asked.