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.

Adding tables to a connected source

A data source covers its whole database or schema, including tables created after you connect it. A daily refresh, between 3:00 and 4:00 AM Pacific time, re-reads the catalog and finds them. What happens next depends on the source’s auto-add setting.

Auto-add on or off

Section titled “Auto-add on or off”
Setting What the daily refresh does with a new table
On (the default) Adds it to the pack and enriches it automatically. Nothing for you to do.
Off Holds it as pending, out of the pack, until you admit it with edisyl data-sources admit, which imports and studies it in one step.

Turn auto-add off when you want to approve each table before people can ask about it.

Terminal window
edisyl data-sources auto-add <id> --off     # new tables wait to be admitted
edisyl data-sources auto-add <id> --on      # new tables are synced and enriched daily

Turning auto-add off changes nothing about tables already in the pack. Turning it on admits every table that’s pending now. To start a new source with auto-add off, pass --no-auto-add-tables or --admit to data-sources create.

Review and admit held tables

Section titled “Review and admit held tables”

  1. See what’s waiting. Held tables stay pending until you add them. Nothing expires.

    Terminal window
    edisyl data-sources pending <id>

  2. Admit the ones you want. Name them by the fully-qualified name pending prints. With no names, every table pending at that moment is admitted.

    Terminal window
    edisyl data-sources admit <id> ANALYTICS.PUBLIC.ORDERS ANALYTICS.PUBLIC.REFUNDS

    Admitting imports each table and studies it: the step that learns what its columns mean and how it joins. --no-study skips the study, but then questions that depend on the table are declined as though the data were absent.

  3. Check with a question you know the answer to. The models list shows the tables exist. Only an ask shows the pack can use them.

    Terminal window
    edisyl data-sources models <id>
    edisyl ask <pack> "How many orders did we refund last month?" --wait

Take a table back out

Section titled “Take a table back out”
Terminal window
edisyl data-sources withdraw <id> ANALYTICS.PUBLIC.REFUNDS

The table leaves the pack and goes back to pending, so admit can bring it back. Withdrawing is one-way for what was built on it: the table’s semantic model and the verified answers that rested on it are archived, and admitting it again later studies it from scratch.

Tables outside the source’s scope

Section titled “Tables outside the source’s scope”

A source only covers the database or schema you connected. A table in another schema isn’t found by the refresh. Add another data source for that schema, on the same connection:

Terminal window
edisyl data-sources create --name "Finance" --connection-id <connection-id> \
  --database PROD --schema FINANCE --pack-id <pack-id>
edisyl data-sources enrich <new-data-source-id>

Report incorrect code

Please provide a detailed description of the incorrect code.