We have launched the Tekst MCP integration, a new way to bring your Tekst data straight into the AI assistants your team already uses, such as Claude and Microsoft Copilot Studio.
What is new
The Tekst MCP integration connects your Tekst workspace to an AI assistant using the Model Context Protocol (MCP), an open standard for securely linking AI assistants to external data and tools. Once connected, your assistant can pull information directly from your workspace and answer questions grounded in your actual data, with no copying and pasting required.
This first release covers read access, so your AI assistant can retrieve and analyze data from Tekst:
- Analyze process mining data, including throughput times, bottlenecks, and variant comparisons
- Review automation execution history and diagnose failures
- Run queries against your analytics data to answer custom questions about ticket volumes, message trends, and automation performance
- Inspect AI model details and performance metrics
- Audit your integrations and team access
Why it matters
More and more teams rely on AI assistants like Claude and Microsoft Copilot in their day-to-day work. The Tekst MCP integration meets your team where they already are: instead of switching between tools, you can ask questions about your processes, automations, analytics, and models in plain language and get answers based on your live Tekst data.
A typical use case is to chat with your analytics and process data to build very specific reports or interactive dashboards. Because the assistant can combine Tekst with the other tools it is connected to, the possibilities are wide open.
How to get started
A workspace admin first enables MCP access under Settings > Security. From there, follow the setup guide for your AI assistant. For the full picture, including what data your assistant can access and example prompts to try, see the Tekst MCP Overview.
Write tools, which will let your AI assistant make changes in Tekst as well, are coming in a future release.
0 comments
Please sign in to leave a comment.