Mcp

I have been using Atlassian MCP with internal Confluence and Jira, and it has been wonderful. Finding internal information is often challenging and time-consuming. To be honest, searching through Jira or Confluence and locating the right information can be really difficult. Create Jira and Confluence API tokens from your internal site profile page. For example: https://internalconfluence.company.com/profile/personal for Confluence and https://jira.company.com/secure/admin/CreateAPIToken!default.jspa for Jira. These URLs may vary depending on your setup. Create an mcp.json file in the .vscode folder for Visual Studio Code, or place this MCP configuration in the appropriate folder for your IDE of choice: { "mcpServers": { "mcp-atlassian": { "command": "uvx", "args": ["mcp-atlassian"], "env": { "JIRA_URL": "https://jira.company.com", "JIRA_USERNAME": "your.email@company.com", "JIRA_API_TOKEN": "your_api_token", "CONFLUENCE_URL": "https://internalconfluence.company.com/wiki", "CONFLUENCE_USERNAME": "your.email@company.com", "CONFLUENCE_API_TOKEN": "your_api_token" } } } } Remember to run podman-desktop or docker desktop. Because this MCP works as a docker container. ...

Junie is intellij`s AI agent, which is very helpful for working on code, I find it better then github copilot because its taks planning and implementation is more helpful then github copilot for me. And couple of months ago I was doing a small demo to show how to use vscode with github copilot and playwright. The idea is LLM will use the playwright and write all tests and it will explore the site, this is good because it feels like you are showing your product to a fresh eyes, when we are writing/developing we may miss many things, this LLM approach is good for learning how others can act and it will find in time how to use the site and it will write the test scenario we want. I Longer details for vscode check here. ...