Skillget

pingfusi

mcp
Security Audit
Fail
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 55 GitHub stars
Code Fail
  • fs module — File system access in harness/adopt.js
  • fs.rmSync — Destructive file system operation in harness/agent-setup.js
  • os.homedir — User home directory access in harness/agent-setup.js
  • fs module — File system access in harness/agent-setup.js
  • os.homedir — User home directory access in harness/ask.js
  • process.env — Environment variable access in harness/ask.js
  • fs module — File system access in harness/ask.js
  • child_process — Shell command execution capability in harness/assist-selftest.js
  • spawnSync — Synchronous process spawning in harness/assist-selftest.js
  • fs.rmSync — Destructive file system operation in harness/assist-selftest.js
  • process.env — Environment variable access in harness/assist-selftest.js
  • fs module — File system access in harness/assist-selftest.js
  • child_process — Shell command execution capability in harness/behavior-runner-selftest.js
  • exec() — Shell command execution in harness/behavior-runner-selftest.js
  • fs.rmSync — Destructive file system operation in harness/behavior-runner-selftest.js
  • process.env — Environment variable access in harness/behavior-runner-selftest.js
  • fs module — File system access in harness/behavior-runner-selftest.js
  • process.env — Environment variable access in harness/behavior-runner.js
  • fs module — File system access in harness/behavior-runner.js
  • child_process — Shell command execution capability in harness/behavior-selftest.js
  • spawnSync — Synchronous process spawning in harness/behavior-selftest.js
  • fs.rmSync — Destructive file system operation in harness/behavior-selftest.js
  • fs module — File system access in harness/behavior-selftest.js
  • child_process — Shell command execution capability in harness/benchmarks/artifact-battery.js
  • spawnSync — Synchronous process spawning in harness/benchmarks/artifact-battery.js
  • fs module — File system access in harness/benchmarks/corpus.js
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.

README.md
 

Pingfusi

About

pingfusi is an MCP that lets AI agents call human reviewers.

Think MTurk for AI agents. With pingfusi your agent can:

  • Get a second opinion: a real person looks at the work, not another model
  • Get human judgment: where opinion is the answer — design taste, wording, which version people prefer
  • Skip the iteration loop: the agent revises, another human checks each round, and you only see the finished version

Quickstart

Set up Pingfusi for your coding agents with a single command.

npx pingfusi setup

Example Prompts

Here are some example prompts you can try with the pingfusi MCP.

feedback about example prompt what you get demo
a naming choice Which name is better for my coffee app: Brewly or Cuppa? use pingfusi poll result
a confusing page Is my pricing page confusing anywhere? use pingfusi comments pinned to what's off
a website clone Clone www.example.com pixel-perfect. use pingfusi a perfectly cloned website copy-anything.com
design taste Make my website not look like AI slop. use pingfusi design feedback
video vibes Does my promo video look right? use pingfusi feedback pinned to timestamps
[?] ask any question that you can think of real human feedback

How it works

Every job is the same loop underneath:

  1. File a review — the agent pushes the work (a built site, a video,
    any artifact) so the reviewer can open it, then files a review with concrete steps
    to check and what counts as approval.
  2. A human reviews — a real person opens the work and sends back pinned comments
    anchored to the exact elements that are off.
  3. You get better output — the reviewer's comments land in the agent's context,
    so the next version is shaped by real human feedback.

Example: you ask for a landing page that doesn't look like AI slop. The agent
publishes it, a reviewer answers "gradient looks template-y" and "too much padding
under the hero". The agent fixes both and refiles; the next reviewer
approves. You come back to a page a human signed off on.

CLI commands

The full command lives in docs/COMMANDS.md.

pingfusi setup                          install + onboarding
pingfusi doctor                         check the install; prints a fix per problem
pingfusi ask "<question>"               ask a human reviewer, from any directory

License

MIT

Reviews (0)

No results found