Work from your editor
Your editor's agent can set Bash up, test it and ask it for you. Add vestra mcp to your editor once, then ask in plain words.
Log in once
In a terminal, run vestra login with your test key (quickstart).
What happens Your key is saved on this computer, and vestra mcp uses it.
Add it to your editor
A stdio server: the command vestra, with the argument mcp. Cursor and Windsurf take this file as it is.
What happens Your editor starts vestra mcp itself, and its agent sees Vestra's tools: init, test, deploy, ask and the rest.
{ "mcpServers": { "vestra": { "command": "vestra", "args": ["mcp"] } }}Or in VS Code
VS Code reads .vscode/mcp.json, where the list is servers and each says its type.
What happens The same tools, in VS Code's agent.
{ "servers": { "vestra": { "type": "stdio", "command": "vestra", "args": ["mcp"] } }}Set Bash up by talking
Ask your editor's agent: "Set up Vestra to answer Tripnest travellers' booking questions."
What happens It calls init, brings you Bash's questions, and writes vestra.yaml into your folder.
Test it
Ask: "Run the tests."
What happens It calls test, waits up to 45 seconds for the verdict, and reads you the reason for any failure.
Ship it to test mode
Ask: "Deploy it."
What happens deploy runs on your computer with your key, and only ever to test mode. Going live is yours to type: vestra deploy --live.
Ask it
Ask as a traveller would: "Ask travel-help, as traveller-42, when my flight on TN-48213 leaves."
What happens It calls ask. An approval is asked right in your editor, when your editor supports it.
Or connect from anywhere
Any MCP client can reach /v1/mcp with your key as a Bearer token: while in preview, on api-staging.vestra.ai (mcp). Cursor takes this file as it is; in VS Code, list it under servers with "type": "http".
What happens The same tools, except deploy: shipping a version stays with you.
{ "mcpServers": { "vestra": { "url": "https://api-staging.vestra.ai/v1/mcp", "headers": { "Authorization": "Bearer vk_test_your_key" } } }}