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.

Add documents

Documents tell a pack what your organization means: policies, definitions, data dictionaries, and process guides. Every answer drawn from a document cites the passage it came from.

Add documents before you connect data. edisyl reads the documents to learn what your tables and columns mean.

  • Documents: PDF, Office files, Markdown, and plain text.
  • Photos and screenshots: .png, .jpg, .webp, and .heic. Add a note that describes what the photo shows. Search matches the note.
  • The maximum size is 50 MiB per file.
  1. Add the documents.

    Open the pack and drag the files onto the pack page.

  2. Check that each document is indexed. A document is ready to use when its status is Indexed.

    Each document shows its status on the pack page.

After a document is indexed, edisyl compiles it in the background. It extracts facts from the document and tests the pack’s answers on it. An ask during this time can return a missing-source gap. Wait for the compile to finish and ask again. Do not teach the same document twice. See How a pack reads documents.

To remove a document, forget it. forget removes the document and everything the pack learned from it. To replace a document, forget the old version and teach the new one.

The assistant calls forget, then teach.

“Forget the old supplier policy and teach the attached new version.”

forget needs the document’s record id. It comes from the teach that added the document, or from an answer that cited it.

Next: Connect a data source. For every teach and forget option, see the Teach & forget reference.

Report incorrect code

Please provide a detailed description of the incorrect code.