Setup guide

Set up app.twiceshy/twiceshy in Goose

communitystreamable_httphealthy

Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.

01Configuration

{
  "mcpServers": {
    "app-twiceshy-twiceshy": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.twiceshy.app"
      ]
    }
  }
}

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

02Steps

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

03Other runtimes

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

04Provenance

config_sourcegenerated from captured install method

last_checked2026-07-08 02:50Z

sourcesOfficial MCP Registry [p1]

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