{"site":{"name":"Koji","description":"AI-native customer research platform that helps teams conduct, analyze, and synthesize customer interviews at scale.","url":"https://www.koji.so","contentTypes":["blog","documentation"],"lastUpdated":"2026-11-18T05:53:40.922Z"},"content":[{"type":"documentation","id":"00262020-a839-45cc-8b20-8bda6efd8444","slug":"mcp-setup-vscode","title":"Connect Koji to VS Code (MCP): Setup Guide for Copilot Chat Engineers","url":"https://www.koji.so/docs/mcp-setup-vscode","summary":"Connect the Koji MCP server to VS Code by adding a .vscode/mcp.json file that points to https://www.koji.so/api/mcp/mcp, then start the server and sign in to Koji in your browser (OAuth 2.1, no API key). The connector is included on the Interviews and Enterprise plans. Once connected, GitHub Copilot Chat in Agent mode can call Koji's 15 tools to list studies, fetch interviews and transcripts, generate reports and create new studies inside the editor. This enables PR descriptions backed by verbatim customer quotes, specs written against real pain points, follow-up studies after bug fixes and pre-deploy sentiment checks. The config holds no secret, so it is safe to commit and share with your team.","content":"**TL;DR:** VS Code supports the Model Context Protocol (MCP) 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, start the server and sign in to Koji in your browser. Once connected, Copilot Chat can list studies, fetch interview transcripts, pull structured answers, and even create new studies, so your editor becomes a research-aware coding environment without leaving the file you're working on. The MCP connector is included on the Interviews and Enterprise plans.\n\n## Why connect Koji to VS Code\n\nMost 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.\n\nThe 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:\n\n- Ask Copilot to write the empty-state copy for a checkout component using verbatim quotes from your last 30 onboarding interviews\n- Generate a one-paragraph PR description that cites the exact pain point a feature solves\n- Have the AI cross-reference a proposed API design against what users said in pricing-research interviews\n- Build a tasklist from a research report without copying a single line by hand\n\nThis 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 output addressable from any AI surface, including the editor.\n\n## Prerequisites\n\nBefore you start, confirm you have:\n\n1. **A recent version of VS Code with MCP support.** MCP servers are configured through `.vscode/mcp.json` or your user settings. If you don't see MCP options in Copilot Chat, update VS Code from the command palette (\"Check for Updates\").\n2. **GitHub Copilot.** MCP runs inside Copilot Chat's Agent mode. Free Copilot users have limited agent access; paid users get the full experience.\n3. **A Koji account on the Interviews or Enterprise plan.** The MCP connector counts as API access, which is part of those two plans. On Free and Insights, Koji refuses the sign-in. See the [Plan Comparison Guide](/docs/plan-comparison-guide) for what each plan includes.\n\nYou don't need an API key. Koji's MCP server uses OAuth 2.1 sign-in: VS Code opens your browser, you sign in to Koji and approve the connection, and VS Code stores the token for you.\n\n## Step 1: Create the MCP configuration file\n\nVS Code looks for MCP server definitions in two places:\n\n- **Workspace-level**: `.vscode/mcp.json` inside your project (best for team-shared configs that get checked into git)\n- **User-level**: your user profile's MCP configuration (best for personal configs you want available in every workspace)\n\nFor most engineering teams, workspace-level is the right default: your whole team gets the same toolset without anyone having to wire it up individually.\n\nCreate `.vscode/mcp.json` with the following content:\n\n```json\n{\n  \"servers\": {\n    \"koji\": {\n      \"type\": \"http\",\n      \"url\": \"https://www.koji.so/api/mcp/mcp\"\n    }\n  }\n}\n```\n\nThat's the whole config. There is no `headers` block and no secret in the file. Koji publishes its OAuth discovery metadata, so VS Code finds the sign-in page on its own and registers itself as a client automatically.\n\n## Step 2: Start the server and sign in\n\nOpen Copilot Chat (Ctrl/Cmd + Alt + I) and switch to **Agent mode** from the dropdown. Open the tools picker above the input box; you should see \"koji\" listed as an available server. Start it (you can also click the **Start** link VS Code shows above the server entry in `mcp.json`).\n\nVS Code asks you to confirm that you trust the server, then opens your browser on a Koji consent page. Sign in with your Koji account, review what the connection is asking for, and approve it. The consent page lists each permission in plain words: reading your studies, interviews and account, and, if the client asks for them, creating and publishing studies, generating and publishing reports, and adding respondents.\n\nWhen you return to VS Code you'll see the Koji tools listed under the server. Access tokens refresh automatically, so you won't be asked to sign in again every session.\n\nIf the server doesn't start or no tools appear, jump to the troubleshooting section at the end of this guide.\n\n## Step 3: Try your first query\n\nIn Agent mode, ask Copilot:\n\n> \"List my Koji studies and tell me which one has the most completed interviews this week.\"\n\nCopilot will call `koji_list_studies`, then for each study call `koji_get_interviews`, 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.\n\n## High-impact VS Code workflows\n\nThe MCP integration becomes really useful when you wire it into your normal engineering rituals. A few patterns that work well:\n\n### Writing PR descriptions backed by research\n\nOpen the diff for a PR, switch to Copilot Chat Agent mode, and prompt:\n\n> \"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.\"\n\nCopilot reads the diff, calls `koji_get_study_data` to fetch structured answers and quality scores, calls `koji_get_transcript` for the highest-quality interviews, and writes a description that includes verbatim evidence. Reviewers like this because the \"why\" is quoted, not asserted.\n\n### Spec'ing new features against real pain points\n\nWhen you start a new feature branch, ask Copilot to brief you:\n\n> \"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.\"\n\nThis 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.\n\n### Closing the loop on bug reports\n\nWhen you fix a bug that came out of a customer interview, ask:\n\n> \"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.\"\n\nThis calls `koji_create_study` with a full question list, which can use any of the 6 structured question types Koji supports (open ended, scale, single choice, multiple choice, ranking, yes/no), and `koji_import_respondents` to add the participants. Closed-loop research without leaving the editor.\n\n### Pre-deploy sentiment check\n\nBefore merging to main on a Friday, run:\n\n> \"Check my last 50 interviews across all studies for any new mentions of 'crash', 'freeze', or 'login'. List the top 5 most urgent.\"\n\nCopilot uses Koji's theme analysis output to scan recent interviews, surfacing anything that should block the release.\n\n## Sharing the config with your team\n\nOnce you have `.vscode/mcp.json` working, commit it to your repository. Every teammate who clones the repo will see the Koji server listed in their Copilot Chat tools. Each person signs in with their own Koji account on first use, so everyone sees only the studies they have access to, and the config file never contains a secret.\n\nSome teams add a one-line note to their `README.md`:\n\n> \"Open Copilot Chat in Agent mode, start the koji MCP server, and sign in to Koji when your browser opens. You need a Koji seat on our Interviews or Enterprise workspace.\"\n\nThis gets new hires productive in their first hour.\n\n## Configuring confirmation prompts for write tools\n\nKoji's MCP server includes 7 write tools: `koji_create_study`, `koji_update_brief`, `koji_publish_study`, `koji_configure_study`, `koji_generate_report`, `koji_publish_report` and `koji_import_respondents`. Each one is only available when you approved the matching write permission on the consent page. You probably do not want Copilot calling these without your explicit approval.\n\nVS Code's MCP implementation asks for confirmation before tool calls by default. You can adjust auto-approval in Settings (search for \"auto approve\" under Chat). We recommend leaving auto-approve off for any tool whose name starts with `koji_create`, `koji_publish`, `koji_configure`, `koji_update` or `koji_import`. Read tools (`koji_list_*`, `koji_get_*`, `koji_export_data`) can usually be auto-approved safely.\n\n## Quick troubleshooting\n\n| Symptom | Likely cause | Fix |\n| --- | --- | --- |\n| Browser sign-in never opens | Popup or default-browser issue | Restart the server from the tools picker and allow koji.so to open |\n| Sign-in completes but the server stays unauthorized | Your account isn't on a plan with API access | The MCP connector needs the Interviews or Enterprise plan |\n| Server starts but no tools listed | Older VS Code version, or permissions not approved | Update VS Code, then restart the server and approve the consent page |\n| \"Connection refused\" or timeout | Corporate network blocks koji.so | Allow `koji.so` and `*.koji.so` in your proxy |\n| Write tools missing | You approved read permissions only | Sign out of the server in VS Code and sign in again, approving the write permissions |\n\nFor a deeper troubleshooting walkthrough, see the dedicated MCP troubleshooting guide linked below.\n\n## Why this matters\n\nStatic 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 different: the AI inside your editor reads live data every time you ask, with each interview's quality score attached and structured by the same questions your research team designed. That makes the research durable: it can be referenced indefinitely without anyone updating a doc.\n\nFor engineering teams that want their code to match what customers said, the VS Code and Koji MCP setup is one of the quickest integrations to get running.\n\n## Related resources\n\n- [Connect Koji to Cursor (MCP)](/docs/mcp-setup-cursor): equivalent setup for Cursor users\n- [Connect Koji to Claude (MCP)](/docs/mcp-setup-claude): Claude Desktop config\n- [Koji MCP Tool Reference](/docs/mcp-tool-reference): full list of 15 tools and their parameters\n- [MCP Troubleshooting Guide](/docs/mcp-troubleshooting): fix common MCP connection and tool errors\n- [Koji Structured Questions Guide](/docs/structured-questions-guide): the 6 question types your MCP queries can target\n- [MCP Authentication and Security](/docs/mcp-authentication-security): how OAuth sign-in and permissions work\n- [MCP Best Practices](/docs/mcp-best-practices): patterns that scale across teams\n\n---\n\n<!-- crosslink:dev-hub -->\n## Related: other ways to connect\n\nThe [Developer Hub](/docs/building-with-ai) is the single starting point for every way to connect to Koji: the MCP server (this section), the REST Headless API, and the embed widget. For a code integration, see [API Authentication](/docs/api-authentication) and [Starting Interviews via API](/docs/starting-interviews-via-api).\n","category":"Claude & MCP Integration","lastModified":"2026-10-20T04:20:24.820548+00:00","metaTitle":"Connect Koji to VS Code via MCP | Copilot Chat Setup Guide","metaDescription":"Step-by-step guide to connect Koji's MCP server to VS Code Copilot Chat Agent mode. Pull live customer interviews, transcripts, and structured answers into your editor without copy-pasting.","keywords":["koji mcp vscode","vscode mcp setup","copilot chat mcp","mcp configuration vscode","user research vscode","customer interviews in vscode","mcp.json","model context protocol vscode"],"aiSummary":"Connect the Koji MCP server to VS Code by adding a .vscode/mcp.json file that points to https://www.koji.so/api/mcp/mcp, then start the server and sign in to Koji in your browser (OAuth 2.1, no API key). The connector is included on the Interviews and Enterprise plans. Once connected, GitHub Copilot Chat in Agent mode can call Koji's 15 tools to list studies, fetch interviews and transcripts, generate reports and create new studies inside the editor. This enables PR descriptions backed by verbatim customer quotes, specs written against real pain points, follow-up studies after bug fixes and pre-deploy sentiment checks. The config holds no secret, so it is safe to commit and share with your team.","aiPrerequisites":["A recent VS Code release with MCP support","GitHub Copilot","A Koji account on the Interviews or Enterprise plan"],"aiLearningOutcomes":["Create a .vscode/mcp.json file with the Koji MCP server block","Use VS Code's secure input prompt to keep your API key out of source control","Verify the connection by listing all 15 Koji MCP tools in Copilot Chat","Run high-impact workflows: research-backed PR descriptions, spec-against-pain, closed-loop follow-ups","Configure confirmation prompts so write tools require explicit approval","Share the MCP config with your team via git without exposing secrets"],"aiDifficulty":"intermediate","aiEstimatedTime":"8 min read"}],"pagination":{"total":1,"returned":1,"offset":0}}