1. Conduid
  2. Blockchain
  3. prompt-protection
MCP server · Blockchain

prompt-protection

by · github.com/mughalhere/prompt-protection

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Unclaimed blockchain
InstallView source
37Low

Scored a month ago · breakdown

About prompt-protection

prompt-protection is an MCP server published by mughalhere in the Blockchain category: scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

Claude Code
claude mcp add prompt-protection -- npx -y prompt-protection
npx
npx -y prompt-protection

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about prompt-protection

Powered by Claude · Grounded in docs

I know everything about prompt-protection. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v4.0.0v4.0.0 · 21 Sep 2026What's Changed 4.0.0-rc.1: stable tier, open unions, guard-first by @mughalhere in https://github.com/mughalhere/prompt-protection/pull/36 chore(release): 4.0.0 by @mughalhere in https://github.com/mughalhere/prompt-protection/pull/38 Full…
v3.1.1v3.1.1 · 15 Sep 2026What's Changed fix(training): publish_hf.py defaults to the logged-in user's namespace by @mughalhere in https://github.com/mughalhere/prompt-protection/pull/26 docs: link the Hugging Face dataset mirror by @mughalhere in…
v3.1.0v3.1.0 · 15 Sep 2026What's Changed feat!: v3.0 agent security runtime — tool-call guard, spotlighting, canaries, embedded ML, datasets by @mughalhere in https://github.com/mughalhere/prompt-protection/pull/21 feat: v3.1 production-grade — fail-closed,…
Questions

About prompt-protection

How do I install prompt-protection?

Run claude mcp add prompt-protection -- npx -y prompt-protection, then add the server to your MCP client's configuration.

Is prompt-protection safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is prompt-protection still maintained?

Yes — the latest release is v4.0.0 (21 Sep 2026), and the last commit was a month ago. The repository has 0 stars.