What is injectshield?

A local MCP server that checks untrusted text for attempts to manipulate an AI agent before the text is sent to a language model. It runs through the @injectshield/mcp npm package and needs an API key and service address.

Use it to scan text from untrusted sources as part of an agent workflow before making language-model calls.

It helps catch prompt-injection attacks before external text can influence an AI agent's instructions or actions.

injectshield — MCP server for Claude Code and Codex by bch1212

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.

Clone the repo

git clone --depth 1 https://github.com/bch1212/injectshield

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

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/bch1212/injectshield/injectshield-mcp-injectshield.svg)](https://agentmods.dev/mcp/bch1212/injectshield/injectshield-mcp-injectshield)

Your own site

<a href="https://agentmods.dev/mcp/bch1212/injectshield/injectshield-mcp-injectshield"><img src="https://agentmods.dev/badge/mcp/bch1212/injectshield/injectshield-mcp-injectshield.svg" alt="Measured on agentmods" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

injectshield 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 6d 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.

packages/injectshield-mcp/server.json · 13 lines

What it actually says

{
  "injectshield": {
    "command": "npx",
    "args": [
      "-y",
      "@injectshield/mcp"
    ],
    "env": {
      "INJECTSHIELD_API_KEY": "",
      "INJECTSHIELD_API_BASE": "https://api.injectshield.dev"
    }
  }
}

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.

6d ago First seen · 13 lines scan A 52fbdf374265

Subscribe to this mod's changes

injectshield is an MCP server published in the GitHub repository bch1212/injectshield (0 stars, last pushed 3mo 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.

Building agents Guardrails Security agent ai ai-security claude cloudflare-pages

injectshield

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

koma-gate-mcp

koma-core-mcp

robinhood

agentguards

promptwall

gatekeeper