Connect Vindex to GitHub Copilot
GitHub Copilot picks up stories in two places: Copilot Chat in VS Code, and the coding agent working an assigned issue. Vindex connects to both, so the story is checked whether a person or the agent is holding it.
Three steps, about 4 minutes. Open to every registered Vindex user; new users create an account during sign-in.
The walkthrough
Add the Vindex MCP server
In VS Code, open the Command Palette and run MCP: Add Server. Choose HTTP, paste the server URL, name it vindex, and pick Workspace to write .vscode/mcp.json for the repository, or Global to use it everywhere.
For the Copilot coding agent, open the repository's Settings, then Copilot, then Coding agent, and add the same server under MCP configuration so the agent can call Vindex while it works an issue.
{
"servers": {
"vindex": {
"type": "http",
"url": "https://mcp.vindexgateway.com/mcp"
}
}
}Sign in with your Vindex account
Start the server from the MCP view or the inline Start action in mcp.json. VS Code asks to allow the sign-in and opens your browser on the Vindex sign-in; use the account you use for the Vindex Portal, or create one to start on the free plan.
When the browser confirms, the server shows as running with three tools. In Copilot Chat, open the tools picker in agent mode and make sure the Vindex tools are selected.
Score your first story
Switch Copilot Chat to agent mode, paste a story, and ask for a Vindex score before any edits. Copilot calls score_story and reports the finding, the percentage, and the band. Confirm the tool call when asked, or allow it for the session.
Pass the issue number or tracker key; Copilot sends it as the story id so the re-check after edits is free.
Try this in GitHub
“Score this story with Vindex before you change anything, story id #214, and tell me whether it is ready: As a returning customer I want to reuse a saved address at checkout so I do not retype it. Acceptance criteria: saved addresses appear as options; selecting one fills the form; the default address is preselected.”
What comes back
The result reads finding first: the one change that moves the score most, in plain language. Then the overall percentage and its band (Healthy 80 to 100, Needs review 60 to 79, At risk 0 to 59), then the six INVEST dimensions with reasons and suggestions when you ask for them.
The band is Vindex’s suggestion. GitHub Copilot does not stop or change anything on its own; what happens next is your call. Fix the story and ask again: the re-check of a counted story is free.
Make the check automatic
Copilot Chat and the coding agent both read .github/copilot-instructions.md. A ready-check rule there applies to every story either of them is handed in the repository.
## Before implementing a story
1. Score it with the Vindex score_story tool. Pass the tracker key as story_id.
2. Healthy: proceed. Draft the acceptance checks from the Testable reasoning before writing code.
3. Needs review or At risk: do not write code. Report the finding and the top
recommendations, and ask the product owner the open questions.The threshold is the team’s to set; see putting a ready check into your agent’s standing instructions.
Troubleshooting
The server shows as running but Copilot does not use it
Open the tools picker in Copilot Chat agent mode and select the Vindex tools. Ask mode does not call tools; switch to agent mode.
The coding agent cannot reach Vindex
Confirm the server is in the repository's Copilot coding agent MCP configuration and that the sign-in for it completed. The agent uses the repository configuration, not your local mcp.json.
The tool returned one sentence and no percentages
That is a Vindex error message: a timeout, a busy company, or an exhausted allowance. Ask Copilot to call get_usage, or try again in a moment.
Using a different client?
Next steps
Finding first, then the band, then the dimensions.
Score before building; proceed on Healthy.
Endpoint, sign-in, tools, limits.
GitHub Copilot was connected to the live Vindex MCP server before this page was published.