Set up caura in Continue

communitystreamable_httphealthy

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

01Configuration

{
  "mcpServers": {
    "caura": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://caura.ai/mcp"
      ]
    }
  }
}

Remote server. This uses the mcp-remote bridge so Continue can reach the hosted endpoint. Add it to ~/.continue/config.yaml.

02Steps

Make sure Continue is installed and up to date.
Open ~/.continue/config.yaml and add the block above (merge into any existing mcpServers).
Provide any required API keys/credentials as environment variables.
Restart Continue and confirm caura’s tools appear.

03Other runtimes

Claude Desktop Cursor Windsurf Cline Goose VS Code OpenAI Agents SDK LangGraph CrewAI

04Provenance

config_sourcegenerated from captured install method

last_checked2026-08-16 22:09Z

sourcesGitHub repo search [p4]

Next step

Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.

Explore Apex →

See also: server page · is it safe? · alternatives