Skip to content
edisyledisyl

Search these docs from your AI tool

  • Antigravity
    {
  "mcpServers": {
    "edisyl-docs": {
      "serverUrl": "https://docs.edisyl.com/mcp"
    }
  }
}
  • Claude CodeCLI
    claude mcp add edisyl-docs https://docs.edisyl.com/mcp --transport http --scope user
  • CodexCLI
    codex mcp add --url https://docs.edisyl.com/mcp edisyl-docs
  • Cursor
    {
  "mcpServers": {
    "edisyl-docs": {
      "type": "http",
      "url": "https://docs.edisyl.com/mcp"
    }
  }
}
  • Gemini CLI
    gemini mcp add --transport http edisyl-docs https://docs.edisyl.com/mcp
  • Goose
    {
  "extensions": {
    "edisyl-docs": {
      "enabled": true,
      "name": "edisyl-docs",
      "type": "streamable_http",
      "uri": "https://docs.edisyl.com/mcp",
      "envs": {},
      "env_keys": [],
      "headers": {},
      "description": "",
      "timeout": 300,
      "bundled": null,
      "available_tools": []
    }
  }
}
  • JetBrains AI Assistant
    {
  "mcpServers": {
    "edisyl-docs": {
      "type": "http",
      "url": "https://docs.edisyl.com/mcp"
    }
  }
}

    Paste into Settings → Tools → AI Assistant → Model Context Protocol → Add → As JSON. Direct file writing isn’t supported — JetBrains stores this per-version as XML.

  • Junie (JetBrains)
    {
  "mcpServers": {
    "edisyl-docs": {
      "url": "https://docs.edisyl.com/mcp"
    }
  }
}
  • OpenCode
    {
  "mcp": {
    "edisyl-docs": {
      "type": "remote",
      "url": "https://docs.edisyl.com/mcp"
    }
  }
}
  • VS CodeCLI
    code --add-mcp '{"name":"edisyl-docs","type":"http","url":"https://docs.edisyl.com/mcp"}'
  • Windsurf
    {
  "mcpServers": {
    "edisyl-docs": {
      "serverUrl": "https://docs.edisyl.com/mcp"
    }
  }
}

    Supports both stdio and native HTTP connections.

Looking to ask a pack from your AI tool instead? That's a different server: see AI clients.

edisyl ask

Terminal window
edisyl ask <pack> "<question>" [flags]

One natural-language question → one synthesized, cited answer over the pack’s knowledge, connections, and data sources, plus any readable upstream packs it composes. Never chooses data-vs-knowledge for you, and never writes SQL for you to read.

<pack> accepts a slug, a name (case-insensitive), or a UUID. Find one with edisyl pack list.

Flags

Section titled “Flags”
Flag Behavior
--wait Block until the answer is ready and print it with its evidence. Server window is ~60s; past that the CLI keeps polling to --timeout.
--timeout <duration> Only with --wait. Default 5m. Raise it for slow data questions: --wait --timeout 20m.
--id-only Print the bare Action id and nothing else; for scripting: action_id=$(edisyl ask "$PACK" "…" --id-only).
--cron "<expr>" Make this a recurring scheduled ask. 30-minute minimum interval. See Scheduling.
--at <RFC3339> Run this ask once, at a future time.
--name <label> Optional human label for a schedule.
-j, --json Machine-readable output.
--quiet Drop hints and banners, keep the data.

Without --wait

Section titled “Without --wait”
Terminal window
action_id=$(edisyl ask "$PACK" "<slow data question>" --id-only)
edisyl action watch "$action_id"    # narrates progress, then prints the answer
edisyl action get "$action_id"      # read the final answer again, any time

When it can’t answer

Section titled “When it can’t answer”

ask won’t fabricate. A decline that names a missing definition is a knowledge-miss → teach. A decline that can’t find or resolve data (“no rows”, “couldn’t resolve”) is a data-miss → task. See Closing gaps.

Terminal statuses

Section titled “Terminal statuses”

Same five as every Action: see action for the full lifecycle, including waiting (the pack needs clarification, and nothing resumes a waiting Action; answer what it names and start a new one).

Report incorrect code

Please provide a detailed description of the incorrect code.