Skip to content
Back to search

pingfusi

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/alex-durango--pingfusi/badge.svg)](/listings/alex-durango--pingfusi)

HTML

<a href="/listings/alex-durango--pingfusi"><img src="/api/listings/alex-durango--pingfusi/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

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

npx pingfusi setup

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 98 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <div align="center">
  3. <a href="https://pingfusi.com">
  4. <picture>
  5. <img alt="pingfusi logo" src="./docs/icon.svg" width="120">
  6. </picture>
  7. </a>
  8. </div>
  9. &nbsp;
  10. <h1 align="center">Pingfusi</h1>
  11. <p align="center">
  12. <a href="https://www.npmjs.com/package/pingfusi" alt="NPM Version">
  13. <img src="https://img.shields.io/npm/v/pingfusi.svg"></a>
  14. <a href="https://www.npmjs.com/package/pingfusi" alt="NPM Downloads">
  15. <img src="https://img.shields.io/npm/dw/pingfusi.svg"></a>
  16. <a href="LICENSE" alt="License">
  17. <img src="https://img.shields.io/badge/license-MIT-blue.svg"></a>
  18. <a href="https://discord.gg/pUKzftBUTY" alt="Discord">
  19. <img src="https://img.shields.io/badge/discord-join-5865F2.svg?logo=discord&logoColor=white"></a>
  20. </p>
  21. </div>
  22. ## About
  23. pingfusi is an MCP that lets AI agents call human reviewers.
  24. Think MTurk for AI agents. With pingfusi your agent can:
  25. * **Get a second opinion**: a real person looks at the work, not another model
  26. * **Get human judgment**: where opinion is the answer — design taste, wording, which version people prefer
  27. * **Skip the iteration loop**: the agent revises, another human checks each round, and you only see the finished version
  28. ## Quickstart
  29. Set up Pingfusi for your coding agents with a single command.
  30. ```sh
  31. npx pingfusi setup
  32. ```
  33. ## Example Prompts
  34. Here are some example prompts you can try with the pingfusi MCP.
  35. | feedback about | example prompt | what you get | demo |
  36. |---|---|---|---|
  37. | a confusing page | `Is my pricing page confusing anywhere? use pingfusi` | comments pinned to what's off | |
  38. | a website clone | `Clone www.example.com pixel-perfect. use pingfusi` | a perfectly cloned website | [copy-anything.com](https://copy-anything.com/) |
  39. | design taste | `Make my website not look like AI slop. use pingfusi` | design feedback | [video](https://youtu.be/AicGxc2aOSg) |
  40. | video vibes | `Does my promo video look right? use pingfusi` | feedback pinned to timestamps | |
  41. Each of these publishes the work first so the reviewer can open it; when in doubt,
  42. publish: a reviewer can only judge what they can see. Text-only questions work too —
  43. if words can carry the whole question, the reviewer just sees the question.
  44. ## Credits
  45. Two lifetime reviews are free. The paid plan includes 100 Pingfusi credits for
  46. $30/month, with no rollover. Game playtesting is available through Qaping, with
  47. its own credits; it is not a Pingfusi review job.
  48. ## How it works
  49. Every job is the same loop underneath:
  50. 1. **File a review** — the agent pushes the work (a built site, a video,
  51. any artifact) so the reviewer can open it, then files a review with concrete steps
  52. to check and what counts as approval.
  53. 2. **A human reviews** — a real person opens the work and sends back pinned comments
  54. anchored to the exact elements that are off.
  55. 3. **You get better output** — the reviewer's comments land in the agent's context,
  56. so the next version is shaped by real human feedback.
  57. Example: you ask for a landing page that doesn't look like AI slop. The agent
  58. publishes it, a reviewer answers "gradient looks template-y" and "too much padding
  59. under the hero". The agent fixes both and refiles; the next reviewer
  60. approves. You come back to a page a human signed off on.
  61. ## CLI commands
  62. The full command lives in [docs/COMMANDS.md](docs/COMMANDS.md).
  63. ```
  64. pingfusi setup install + onboarding
  65. pingfusi doctor check the install; prints a fix per problem
  66. pingfusi ask "<question>" ask a human reviewer, from any directory
  67. pingfusi studio [ping_id] local viewer for review results —
  68. sessions, recordings, transcripts, key moments,
  69. agent findings (contract: docs/STUDIO.md)
  70. ```
  71. ## License
  72. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.