Claude Code

Claude Code supports MCP out of the box. Two minutes total.

InstallCopy Anchor Link

Run this in a terminal. It's the command Connect › Get started gives you:

claude mcp add --transport http caura https://caura.dev/mcp/ --header "X-API-Key: mc_xxx"

Add --scope user to use Caura in all your projects, or --scope project to write it to a .mcp.json at the repo root that your team shares (the key goes into that file). To write the file by hand, give the entry "type": "http"; Claude Code doesn't load an entry without it:

{
"mcpServers": {
  "caura": {
    "type": "http",
    "url": "https://caura.dev/mcp/",
    "headers": { "X-API-Key": "mc_xxx" }
  }
}
}

Restart Claude Code. The caura_* tools become available — Claude Code will surface them to you on first use and ask permission like any other tool.

Going to production: use a per-agent keyCopy Anchor Link

The mc_ quickstart key above is a tenant-scoped credential — fine for personal use. Anything that ships a fleet of agents should bind each agent to its own agent-scoped credential for trust gating, fleet membership, and per-agent keystones. The MCP server accepts the credential on either X-API-Key: mc_… or Authorization: Bearer mc_… — both tenant-scoped and agent-scoped credentials share the mc_ prefix; scope is set at mint time. See Per-agent keys for the atomic provisioning flow.

Using itCopy Anchor Link

Just talk to the model:

Remember that this repo uses pnpm, not npm.

What did we decide about the auth flow?

The tool calls happen automatically. See the full tool surface in the agent skill at /docs/agents.

TipsCopy Anchor Link

• tenant_id is set by your key: an mc_ key belongs to one tenant. To keep repos' memories apart, give each repo its own tenant and key, or its own fleet_id.

• The Caura memclaw skill (~/.claude/skills/memclaw) ships richer prompting. Install it:

  curl -s "https://caura.dev/api/v1/install-skill?agent=claude-code" | bash

Capture work automatically — the InterviewerCopy Anchor Link

The steps above let Claude Code call Caura. Separately, the Interviewer can read Claude Code's own session transcripts on a schedule and synthesize what the agent did — decisions, outcomes, blockers — into typed memories, with no caura_write calls. It's read-only, opt-in per tenant, and gated behind a project allowlist. See Interviewer → Setup.