setupLABSCO SUMMARY
It closes the loop LLMs cannot close on their own.
A model will generate ten variants and then guess which one a person prefers. Handing that judgement to a panel and picking the result back up in the same conversation turns it from a guess into data — A/B preference, ratings, rankings, or a human gate before an agent ships something irreversible.
What it is
A server over Datapoint AI, which recruits human annotators. From the conversation you design a survey from a plain-language description, launch it to a panel, and read status and aggregated results as they come in. Text, images, audio and video are all supported as material.
What you get
- A survey designed from a natural-language description, before anything is launched
- The survey launched to a panel of real people
- Local images, audio or video uploaded so they can be used as survey material
- Status, progress and aggregated results while it runs
- Raw per-annotator responses, paginated, when the aggregate is not enough
- All your surveys listed
- A running survey paused and resumed — in-flight responses keep arriving while it is paused
- A survey cancelled permanently, with unused reserved credits refunded
- Account balance checked, and a checkout link to top it up
Requirements
uv on your PATH, and a Datapoint AI account — the first run opens a browser to authenticate. Surveys are paid for in credits, and cancelling refunds the reserved credits you did not use.
Setup effort
One command plus credentials — uvx --from git+https://github.com/impel-intelligence/datapoint-mcp.git datapoint-mcp, then supply credentials
USE CASES
01
Settling an A/B argument with actual people
Describe the comparison, review the plan it produces, then launch it and read the aggregate.
02
Testing creative that is not text
Upload the images, audio or video first, then build the survey around them.
03
Gating an agent before it does something irreversible
Put the decision to a panel and hold until the results come back rather than letting the model decide alone.
04
Digging into a result that looks odd
Page through the raw per-annotator responses instead of trusting the aggregate that surprised you.
05
Stopping a run that is going the wrong way
Pause task serving while you decide, then resume it, or cancel and take the unused credits back.
06
Keeping track of spend and what is running
List your surveys and read the balance before launching the next one.
12 tools
Listed in project docs. Your client may show a different list.
upload_mediaplan_surveycreate_surveycheck_surveyget_survey_responseslist_surveyspause_surveyresume_surveycancel_surveycheck_balanceadd_creditsBEFORE YOU INSTALL
What to know first
Tools you get
12 tools named in the project's documentation.
INSTALLATION
Connect your client
Server setup
Any MCP client
TERMINAL
uvx --from git+https://github.com/impel-intelligence/datapoint-mcp.git datapoint-mcpMCP Clients
Claude Code — plugin
CLAUDE CODE — PLUGIN · IN CLIENT
/plugin marketplace add impel-intelligence/datapoint-mcp
/plugin install datapoint@datapointClaude Code, Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"datapoint": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/impel-intelligence/datapoint-mcp.git",
"datapoint-mcp"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"datapoint": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/impel-intelligence/datapoint-mcp.git",
"datapoint-mcp"
]
}
}
}
