A local connection to PromptingBox, a service for saving, searching, and discovering prompts used with AI coding tools. It runs through an npm package and requires a PromptingBox API key.

Use it to save, find, and manage prompts from Claude, Cursor, and ChatGPT through an MCP connection.

It gives developers a way to keep prompts in one searchable place instead of losing useful instructions across separate chats and tools.

pbox — MCP server by promptingbox

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/promptingbox/mcp/pbox

Clone the repo

git clone --depth 1 https://github.com/promptingbox/mcp

Made for: Claude Code, Codex, Cursor.

Or install pbox, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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 59% copy Near-identical to another mod in the catalogue.

Security

Grade A, and why

pbox 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.

Origin

This is a copy

59% identical to playwright — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugin/.mcp.json · 12 lines

What it actually says

{
  "pbox": {
    "command": "npx",
    "args": [
      "-y",
      "@promptingbox/mcp"
    ],
    "env": {
      "PROMPTINGBOX_API_KEY": ""
    }
  }
}

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 · 12 lines scan A d653fc362345

Subscribe to this mod's changes

pbox is an MCP server published in the GitHub repository promptingbox/mcp (0 stars, last pushed 5mo 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. It is 59% identical to playwright, differing in 9 lines, and is treated as a copy.

Data and AI Prompting

pbox

Getting it into your agent

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

compactprompt

polyprompt

pqs-mcp-server

meta-prompt-mcp

thinking-prompts

prompt-compass