mcpbeat Sign in

Injectcheck MCP Server

local only

Injectcheck runs on your own machine — the client starts it, so there is no endpoint to ping. 2 128 installs a week from npm. Last commit 23 Oct 2026.

Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.

Installs per day peak 2 128 · avg 70
a month agotoday
2 128
Installs / week
npm · @reneturcios/injectcheck
0
Stars
0 open issues
23 Oct 2026
Last commit
20 releases in 90 days
MIT
License
TypeScript

Nothing serious here today

Today is the operative word: we check Injectcheck every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add injectcheck -- npx -y @reneturcios/injectcheck
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "injectcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/injectcheck"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.injectcheck]
command = "npx"
args = ["-y", "@reneturcios/injectcheck"]
.cursor/mcp.json
{
  "mcpServers": {
    "injectcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/injectcheck"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "injectcheck": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/injectcheck"
      ]
    }
  }
}

Alternatives to Injectcheck

same job, measured the same way
Agent Skill & Config Security Audit
by tylerscomic-lab

Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

answering
Agentglass
by agentglass

Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.

1 tools answering
Cloakcheck
by vercel-cloakcheck-wheat

Scan a page for hidden prompt-injection payloads targeting AI agents.

1 tools answering
Prompt Injection Scanner
by openkrill

Check text before your agent reads it: hidden instructions, invisible text and links that leak data.

5 tools answering
Injectshield
by bch1212

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

9 installs/wk local only
AI Code Scanner
by guardbee

Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

563 installs/wk local only
AI Code Scanner
by 4hmetuyar

Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

local only
AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall
by agentdiet

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

2 tools answering

Injectcheck — questions

Answers built from our own checks of this server.

Why is there no uptime for Injectcheck?
Injectcheck runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @reneturcios/injectcheck was installed 2 128 times last week.
How do I connect Injectcheck?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @reneturcios/injectcheck straight from npm; nothing to host, nothing to sign up for.
How many people use Injectcheck?
The npm package @reneturcios/injectcheck was installed 2 128 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Injectcheck open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.