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 builds context your agents can trust

Turn your documents and data into cited answers for every use case, and confidently keep your agents working as they change.

What is a Knowledge Pack?

edisyl builds Knowledge Packs. A pack holds the documents, data and definitions behind one job, and gives any agent that asks it the same cited answer every time. You build one pack per use case, for any job your organization runs, from root-cause analysis on a production line to a weekly supplier review, and point your agents at the packs their jobs need.

Build a packConnect your agent

Why a Knowledge Pack

Section titled “Why a Knowledge Pack”

Ask an agent the same question ten times and you can get ten different answers, with citations that go missing or point at the wrong passage. That is an accuracy problem, and a person checking each answer by hand does not scale.

Each pack focuses on a single use case, so it can be trained until it gets that job right. It reads every question through the same Lexicon and answers from the same plan, so the answer stays the same however the question is phrased and whoever asks it.

A pack isn’t limited to the amount of context a model can hold. It can span thousands of pages and a whole warehouse, and for each question it follows a verified plan straight to the passages and tables that question needs. It reads only those, so your tokens go to the answer instead of to everything else in the pack. Calibration holds each plan to a cost target alongside accuracy and speed, so that efficiency is measured, not assumed.

Build a pack for every job you hand to an agent, and your agents can take on as many tasks as you have packs. Hundreds of agents can ask one pack without a person reviewing each answer, because the pack is calibrated before anyone relies on it.

How edisyl compares

Section titled “How edisyl compares”

Other tools give you access to everything and leave you to work out what matters. A pack is curated for one job, so your agent gets just what that job needs. Definitions and rules live in the pack, not in each person’s prompts. Every answer cites the passage or table behind it, and every ask is kept as an Action with a full history.

CapabilityedisylEnterprise searchAI assistantsWarehouse AI
Defines metrics Built from your documents and dataNone of its ownNone. The user explains itHand-built by the data team
Validates data Each definition checked against the data before it is storedNo. Users cross-checkNoPartly. An author verifies
Highlights gaps Says what is missing instead of guessingNot documentedNot consistentlyAsks to clarify
Cites sources Every claim, documents and dataOn documentsWhen searching web or filesShows the SQL
Learns from corrections Taught once, with a receiptThumbs up or downCustom instructionsThe data team curates
Scales past context limits No token limit. Each question gets just what it needsReturns matching documentsThe model's context windowThe tables in scope
Works in your tools Inside the AI tools you already useTheir own appTheir own chat appInside the warehouse
AI assistants means a general AI chat tool used on its own; edisyl works inside them. Warehouse AI means the AI built into a data warehouse.

Next questions

Section titled “Next questions”

How do I connect my data and documents?

Documents first, then data sources, then the questions it must answer. Build a pack →

Maintaining a healthy pack

Your team owns the pack; calibration re-tests it after every change and holds accuracy, speed and cost to target. Keep a pack healthy →

To go deeper, start with Knowledge Packs and Ask, Teach, Task.

Report incorrect code

Please provide a detailed description of the incorrect code.