Skip to main content

Getting started with AI

Comindwork integrates AI capabilities that allow you to query, analyze, and interact with your workspace data using natural language. This page provides an overview of the AI features and how to get started.

AI capabilities overview​

FeatureDescriptionStatus
MCP toolsConnect external AI assistants (Claude, ChatGPT, etc.) to your Comindwork dataAvailable
AI AssistantIn-app AI chat for workspace queriesIn development

MCP - the fastest way to start​

The Model Context Protocol (MCP) lets you connect your Comindwork data to any AI tool that supports MCP. This is the recommended way to start using AI with Comindwork.

What you can do with MCP​

  • Query data - "Show me all open tickets assigned to me"
  • Aggregate and analyze - "How many tasks were completed last month, broken down by team?"
  • Search - "Find records mentioning 'budget approval'"
  • View history - "What changes were made to TASK123 last week?"
  • Read attachments - AI can read images and documents attached to records

Quick setup​

  1. Get your MCP server URL and authentication token from your Comindwork administrator
  2. Add the MCP server to your AI tool:
    • Claude Desktop - add to claude_desktop_config.json
    • Claude Code - add to .mcp.json
    • VS Code - configure in MCP extension settings
  3. Start asking questions about your data

See MCP tools for the detailed setup guide.

How AI accesses your data​

AI tools interact with Comindwork through a structured API layer:

  1. Your AI tool sends a natural language query
  2. The MCP server translates it into API calls
  3. Comindwork returns the data (respecting your permissions)
  4. The AI tool formats and presents the results

Key points:

  • AI access respects the same permissions as your user account - you only see data you are authorized to view
  • Responses are formatted as compact markdown/tables to minimize token usage
  • Field descriptions, prefixes, and suffixes from the app schema are included so the AI understands the data context

Security and privacy​

  • Authentication - MCP connections require a valid token tied to your user account
  • Permissions - all queries respect workspace and app-level access controls
  • Data handling - data is sent to the AI provider you are using (e.g., Anthropic for Claude). Review your organization's data sharing policies before connecting AI to workspaces with sensitive data
  • Token management - tokens should be rotated periodically and revoked when no longer needed

MCP access can be restricted at both workspace and app levels. Sensitive fields (passwords, API keys) are automatically detected and filtered before reaching the AI provider.

Next steps​