Skip to content

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.

Teach & ask

Teach the pack your business knowledge: definitions, the names your team uses, and decisions your data does not record. Then start asking questions.

To upload files, see Add documents. To set up a pack for your team from start to finish, see Set up a Knowledge Pack.

  1. Teach it a fact.

    Say the fact in chat. The assistant calls teach. It returns a queued Action.

    “Teach the growth-metrics pack that an active wallet is any address with a swap in the last 30 days.”

  2. Wait for it to be indexed. Ingestion runs asynchronously. edisyl chunks, embeds, indexes, and organizes the content. A teach is done only when its content can be retrieved.

    The assistant calls action_get until the teach reaches a final status.

    “Tell me when that teach is indexed.”

  3. Ask your first question.

    Ask in chat. The assistant calls ask. It waits about 55 seconds for the answer. A slower answer is followed with action_get.

    “Ask the growth-metrics pack what counts as an active wallet.”

Use ask for every question from now on. You ask one question in plain language and get one cited answer. The answer draws on the pack’s knowledge, connections, and data sources. You never choose between data and knowledge, and you never write SQL.

The assistant calls ask for each question.

“Ask the growth-metrics pack how many swaps happened in the last 7 days.”

Get the Action id and follow the Action instead of waiting:

The assistant calls ask with wait set to false. It gets the Action back at once. It then calls action_get to read the answer.

“Start that question on the growth-metrics pack and check back on it later.”

The assistant calls forget. It removes one ingested document and all knowledge created from it. The document’s id is in the teach’s result.

“Forget the document I just taught.”

You now have the whole loop: connect, teach, ask. To get a pack ready for its users with objectives and calibration, see Set up a Knowledge Pack.

Next: Improving answers. It covers what to do when ask returns an answer that is not good enough.

Report incorrect code

Please provide a detailed description of the incorrect code.