Connect Koji to VS Code (MCP): Setup Guide for Copilot Chat Engineers

TL;DR: VS Code 1.97+ has native Model Context Protocol (MCP) support inside GitHub Copilot Chat's Agent mode. Adding Koji's MCP server takes about three minutes: create a .vscode/mcp.json file in your workspace (or add to your user settings), paste the Koji server block, and authenticate with your Koji API key. Once connected, every Copilot Chat session can list studies, fetch interview transcripts, pull structured answers, and even create new studies — turning your editor into a research-aware coding environment without ever leaving the file you're working on.

Why connect Koji to VS Code

Most engineering teams already live in VS Code. When a PRD lands, you read it there. When a ticket gets groomed, the spec gets pasted into a comment there. When a senior engineer reviews a PR, they leave inline feedback there. But the customer evidence that should be driving every one of those decisions usually lives somewhere else — a Notion doc, a research repo, a Loom recording, a Slack thread — and that distance is where bad product decisions get made.

The Koji MCP integration closes that gap. With MCP wired into VS Code, GitHub Copilot Chat can pull live customer interviews, structured answers, theme analyses, and full study reports directly into the conversation you're already having about code. That means you can:

• Ask Copilot to write the empty-state copy for a checkout component using verbatim quotes from your last 30 onboarding interviews
• Generate a one-paragraph PR description that cites the exact pain point a feature solves
• Have the AI cross-reference a proposed API design against what users said in pricing-research interviews
• Build a tasklist from a research report without copying a single line by hand

This is the modern alternative to manual research-to-code workflows. Tools like Koji automate the heavy lifting — transcription, quality scoring, structured answer extraction, theme generation — and the MCP server makes that automated output addressable from any AI surface, including the editor.

Prerequisites

Before you start, confirm you have:

1. VS Code 1.97 or later. MCP became generally available with the February 2026 release. To check, open VS Code and run "About Visual Studio Code" from the command palette.
2. GitHub Copilot subscription. MCP runs inside Copilot Chat's Agent mode. Free Copilot users now have limited agent access; paid users get the full experience.
3. A Koji account. The MCP server is available on every plan including Free, so you do not need to upgrade to try it.
4. A Koji API key. Generate one in Koji under Settings → API Keys. Treat this key like a password — anyone with it can read your studies and create new interviews.

Step 1: Create the MCP configuration file

VS Code looks for MCP server definitions in two places:

• Workspace-level: .vscode/mcp.json inside your project (best for team-shared configs that get checked into git)
• User-level: through Preferences: Open User Settings (JSON) under the mcp key (best for personal configs you want available in every workspace)

For most engineering teams, workspace-level is the right default — your whole team gets the same toolset without anyone having to wire it up individually.

Create .vscode/mcp.json with the following content:

{
  "servers": {
    "koji": {
      "type": "http",
      "url": "https://www.koji.so/api/mcp/http",
      "headers": {
        "Authorization": "Bearer ${input:koji-api-key}"
      }
    }
  },
  "inputs": [
    {
      "id": "koji-api-key",
      "type": "promptString",
      "description": "Koji API key from app.koji.so → Settings → API Keys",
      "password": true
    }
  ]
}

The inputs block is important: it tells VS Code to prompt you for the key the first time you use the server and store it securely in the OS keychain. The literal API key never lives in the JSON file, which means it stays out of git history even if the config file is committed.

Step 2: Start the server and authenticate

Open Copilot Chat (Ctrl/Cmd + Alt + I) and switch to Agent mode from the dropdown. Click the tools icon (🔧) above the input box. You should see "koji" listed as an available server. Click "Start" — VS Code will prompt you for the API key, and you'll see a green dot next to "koji" once the handshake succeeds.

If the dot is red or yellow, jump to the troubleshooting section at the end of this guide.

Step 3: Try your first query

In Agent mode, ask Copilot:

"List my Koji studies and tell me which one has the most completed interviews this week."

Copilot will call koji_list_studies, then for each study call koji_get_interviews filtered by recent completions, and present a ranked summary. You will see each tool call appear as an expandable block in the chat so you can audit exactly what data was pulled.

High-impact VS Code workflows

The MCP integration becomes really powerful when you wire it into your normal engineering rituals. A few patterns Koji teams already run:

Writing PR descriptions backed by research

Open the diff for a PR, switch to Copilot Chat Agent mode, and prompt:

"Read my changes and write a PR description. Pull customer quotes from the study pricing-page-v2 to justify the change. Filter to interviews with quality score 4 or above."

Copilot reads the diff, calls koji_get_study_data to fetch structured answers, calls koji_get_transcript for the highest-quality interviews, and writes a description that includes verbatim evidence. Reviewers love this because the "why" is no longer trust-me — it's quoted.

Spec'ing new features against real pain points

When you start a new feature branch, ask Copilot to brief you:

"Before I start on the new search feature, summarize the top 5 themes from my search-pain-points study and identify the structured answers where users rated discoverability below 3 on the scale question."

This works because Koji's MCP server returns per-question aggregations — averages, distributions, and option counts — so the AI can do real quantitative reasoning, not just text retrieval.

Closing the loop on bug reports

When you fix a bug that came out of a customer interview, ask:

"Create a Koji study called 'Search relevance fix follow-up' with the participants from my previous search study who reported issues. Use a hybrid interview mode with 4 questions about whether the new behavior fixed their problem."

This calls koji_create_study with a full StudyQuestion array — including the 6 structured question types Koji supports (open_ended, scale, single_choice, multiple_choice, ranking, yes_no) — and koji_import_respondents to seed the panel. Closed-loop research without leaving the editor.

Pre-deploy sentiment check

Before merging to main on a Friday, run:

"Check my last 50 interviews across all studies for any new mentions of 'crash', 'freeze', or 'login'. List the top 5 most urgent."

Copilot uses Koji's theme analysis output to scan recent interviews, surfacing anything that should block the release. This is the kind of safety net you cannot easily build without an MCP-style integration.

Sharing the config with your team

Once you have .vscode/mcp.json working, commit it to your repository. Every teammate who clones the repo will see the Koji server listed automatically in their Copilot Chat tools panel. They will each be prompted for their own API key on first use — the config file itself never contains a secret.

Some teams add a one-line note to their README.md:

"Open VS Code, run Workspace: Add MCP Server if Copilot Chat does not auto-detect, then paste your Koji API key when prompted. Get a key at app.koji.so/settings/api-keys."

This gets new hires productive in their first hour.

Configuring confirmation prompts for write tools

Koji's MCP server includes 8 write tools — koji_create_study, koji_update_brief, koji_publish_study, koji_generate_report, koji_publish_report, koji_configure_study, koji_export_data, koji_import_respondents. You probably do not want Copilot calling these without your explicit approval.

VS Code's MCP implementation shows a confirmation dialog for every tool call by default. You can adjust this in Settings under chat.tools.autoApprove. We recommend leaving auto-approve OFF for any tool whose name starts with koji_create, koji_publish, koji_export, or koji_import. Read tools (koji_list_*, koji_get_*) can usually be auto-approved safely.

Quick troubleshooting

For a deeper troubleshooting walkthrough, see the dedicated MCP troubleshooting guide linked below.

Why this matters

Static surveys, screenshotted quotes, and stale PDF reports have always been the weakest part of customer research. They get out of sync the moment they're produced. The MCP integration is fundamentally different: the AI inside your editor reads live data every time you ask, filtered by Koji's quality gate (interviews scoring 3 or above) and structured by the same schema your research team designed. That makes the research durable — it can be referenced indefinitely without anyone updating a doc.

For engineering teams that want their code to actually match what customers said, the VS Code + Koji MCP setup is one of the highest-leverage 5-minute integrations available.

Related resources

• Connect Koji to Cursor (MCP) — equivalent setup for Cursor users
• Connect Koji to Claude (MCP) — Claude Desktop config
• Koji MCP Tool Reference — full list of 15 tools and their parameters
• MCP Troubleshooting Guide — fix common MCP connection and tool errors
• Koji Structured Questions Guide — the 6 question types your MCP queries can target
• MCP Authentication and Security — best practices for protecting your API key
• MCP Best Practices — patterns that scale across teams