A local MCP server for Datapoint, a service for collecting human opinions and evaluations. It runs from a Python package located with the plugin.

Use it to connect an agent to Datapoint for surveys, comparisons, ratings, rankings, or human-evaluation data.

It gives an agent access to Datapoint through a standard tool connection without separately installing the server package.

datapoint — MCP server by impel-intelligence

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/impel-intelligence/datapoint-mcp/datapoint

Clone the repo

git clone --depth 1 https://github.com/impel-intelligence/datapoint-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

datapoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 11 lines

What it actually says

{
  "datapoint": {
    "command": "uvx",
    "args": [
      "--refresh",
      "--from",
      "${CLAUDE_PLUGIN_ROOT}",
      "datapoint-mcp"
    ]
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 11 lines scan A 1a05b9b6231b

Subscribe to this mod's changes

datapoint is an MCP server published in the GitHub repository impel-intelligence/datapoint-mcp (6 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics ai-agents ai-evaluation annotation anthropic claude claude-code

rebuild-dossier

MCP server "rebuild-dossier" as configured in Parker-Fawcett/rebuild-dossier. Runs locally from the rebuild-dossier npm package.

Parker-Fawcett/rebuild-dossier · not measured

grandjury

GrandJury SDK — submit LLM traces for human evaluation + analytics client. Runs locally from the grandjury Python package.

humanjudge/grandjury · not measured

anno

MCP server "anno" as configured in philmingdao/anno. Runs ./dist/index.js with node.

philmingdao/anno · not measured

md-log-mcp

Model Context Protocol server (stdio + remote Streamable HTTP) that lets agents save .md files (with images) straight into md-log. A thin authenticated HTTP client over the hosted md-log service. Runs locally from the md-log-mcp npm package. Needs 2 environment variables to run.

md-log/md-log-mcp · not measured

gpu

Agent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop. Remote server at joinmultiplayer.ai.

yukakust/joinmultiplayer.ai · not measured

copick-mcp

MCP server for Copick. Runs locally from the copick-mcp Python package.

copick/copick-mcp · not measured