QualiTaTi MCP server
Commit Sep 13, 2026Enables AI agents to conduct AI-moderated interviews, build conversational surveys, and perform qualitative analysis.
Also known as lanceyuu/qualitati-agent-plugins, qualitati-agent-plugins
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.3
- Last commit
- Sep 13, 2026
- License
- MIT
What is QualiTaTi MCP?
QualiTaTi enables AI agents to conduct AI-moderated interviews, build conversational surveys, and perform qualitative analysis.
Summary generated from the project's README
About QualiTaTi MCP server
QualiTaTi allows AI agents to manage qualitative research workflows including AI-moderated interviews, conversational surveys, and data analysis. Developers can integrate this server into clients like Claude Code, Cursor, Codex, and Claude Desktop to automate the setup of interview studies and the processing of participant responses. The agent handles the administrative side of research, such as creating projects and reading transcripts, while human participants interact with the actual study via a shared link.
To use the server, you need a QualiTaTi account and a personal API key starting with qt_. You can configure the connection using an environment variable or through OAuth 2.1 if your client supports dynamic client registration. The server provides specific tools for project management, interview tracking, and qualitative analysis. It also includes specialized commands like /qualitati:new-study and /qualitati:results to streamline research tasks within your preferred development environment.
What you can do with it
- 1Set up interview studiesAsk the agent to create a new research project and generate a link for participants.
- 2Build conversational surveysInstruct the AI to construct a survey by adding specific questions and publishing it.
- 3Analyze qualitative dataRequest a summary or a coding analysis of the interview transcripts collected.
- 4Monitor interview progressHave the agent check the completion status of ongoing interviews and read the full transcripts.
Written from the project's README. Every use case is checked against a quote from it.
How to install QualiTaTi MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall QualiTaTi MCP in Claude Code
$ claude mcp add --transport http qualitati-agent-plugins https://api.qualitati.com/mcpInstall QualiTaTi MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"qualitati-agent-plugins": {
"url": "https://api.qualitati.com/mcp"
}
}
}Install QualiTaTi MCP in VS Code
.vscode/mcp.json
{
"servers": {
"qualitati-agent-plugins": {
"type": "http",
"url": "https://api.qualitati.com/mcp"
}
}
}Install QualiTaTi MCP in VS Code CLI
$ code --add-mcp '{"name":"qualitati-agent-plugins","type":"http","url":"https://api.qualitati.com/mcp"}'Install QualiTaTi MCP in Codex
$ codex mcp add qualitati-agent-plugins --url https://api.qualitati.com/mcpInstall QualiTaTi MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.qualitati-agent-plugins] url = "https://api.qualitati.com/mcp"
Install QualiTaTi MCP in Gemini CLI
$ gemini mcp add -s user --transport http qualitati-agent-plugins https://api.qualitati.com/mcpInstall QualiTaTi MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"qualitati-agent-plugins": {
"url": "https://api.qualitati.com/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablelanceyuu/qualitati-agent-plugins is public and reachablegithub.com/lanceyuu/qualitati-agent-plugins ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-13github.com/lanceyuu/qualitati-agent-plugins ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubQualiTaTi for AI agents
Run AI-moderated interviews, conversational surveys and qualitative analysis on QualiTaTi from Claude Code, Codex, OpenCode, Cursor, Claude Desktop or any MCP client.
One hosted MCP server does the work; this repo packages it as an installable plugin for the tools that have plugin systems and documents the one-line config for the rest. The plugin adds three skills that teach the agent QualiTaTi's workflows (setting up an interview study, building a survey, reading results) and two slash commands.
Prerequisites
- A QualiTaTi account — free tier is fine.
- A personal API key: qualitati.com → Profile → API keys (keys start with
qt_). The key inherits your plan, quotas and billing; revoke it there any time. - Put it in your shell:
export QUALITATI_API_KEY=qt_…
Clients that implement MCP authorization (OAuth 2.1 with dynamic client registration) can skip the key entirely: point them at the server URL and a QualiTaTi consent page opens in your browser. Claude Code: claude mcp add --transport http qualitati https://api.qualitati.com/mcp, then /mcp → Authenticate.
Install
Claude Code
/plugin marketplace add lanceyuu/qualitati-agent-plugins
/plugin install qualitati@qualitati-agent-plugins
You get the qualitati MCP server (reads QUALITATI_API_KEY), the skills, and /qualitati:new-study and /qualitati:results. Without the plugin, the server alone:
claude mcp add --transport http qualitati https://api.qualitati.com/mcp \
--header "Authorization: Bearer $QUALITATI_API_KEY"
Codex CLI / app
codex plugin marketplace add lanceyuu/qualitati-agent-plugins
codex plugin add qualitati@qualitati-agent-plugins
Or configure the server directly in ~/.codex/config.toml:
[mcp_servers.qualitati]
url = "https://api.qualitati.com/mcp"
bearer_token_env_var = "QUALITATI_API_KEY"
OpenCode
{
"mcp": {
"qualitati": {
"type": "remote",
"url": "https://api.qualitati.com/mcp",
"enabled": true,
"headers": { "Authorization": "Bearer {env:QUALITATI_API_KEY}" }
}
}
}
Cursor
.cursor/mcp.json (or use the Add to Cursor button on https://qualitati.com/developers):
{
"mcpServers": {
"qualitati": {
"url": "https://api.qualitati.com/mcp",
"headers": { "Authorization": "Bearer qt_your_key_here" }
}
}
}
Claude Desktop
Custom connectors cannot send a fixed header yet, so bridge with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"qualitati": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.qualitati.com/mcp",
"--header", "Authorization: Bearer qt_your_key_here"]
}
}
}
MCP Registry
Listed as io.github.lanceyuu/qualitati on the official MCP Registry (server.json in this repo), so registry-aware clients and directories find it without any of the above.
What the agent can do
| Tool | What it does |
|---|---|
project_list, project_get, project_create, project_share |
find or set up an interview study and get the participant link |
project_interviews, interview_get, interview_import |
see completion status, read full transcripts, import external transcripts |
analysis_run, analysis_results, analysis_summary, analysis_digest |
run and read quality + coding analysis, digests, counts |
survey_create, survey_add_question, survey_publish |
build a conversational survey and publish it |
A human participant still conducts the interview via the share link; the agent sets studies up and reads the results.
Repo layout
One plugin, two package layouts, shared skills:
.claude-plugin/marketplace.json Claude Code marketplace (this repo, plugin source "./")
.claude-plugin/plugin.json Claude Code plugin manifest
.agents/plugins/marketplace.json Codex marketplace (this repo, plugin path "./")
.codex-plugin/plugin.json Codex plugin manifest (mcpServers -> ./mcp.json, so Codex reads the bearer_token_env_var form)
plugin.json mcp.json Codex / Agent Plugins (Open Plugins) manifest + MCP config
.mcp.json Claude Code MCP config
skills/ commands/ assets/ shared
server.json MCP Registry entry
The repo root is the plugin (the Open Plugins layout cursor.directory scans), and the two marketplace files let Claude Code and Codex install it from the same repo.
License
MIT. QualiTaTi is a product of QualiTaTi (contact@qualitati.com).
QualiTaTi MCP questions
How do I add QualiTaTi MCP to Claude Code?
Run claude mcp add --transport http qualitati-agent-plugins https://api.qualitati.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add QualiTaTi MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does the AI agent conduct the interview itself?
No, the agent manages the setup and reads the results, but a human participant conducts the interview via a shared link.
What specific tasks can the agent perform?
The agent can create interview studies, build conversational surveys, read transcripts, and run qualitative coding analysis.