MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Security-focused MCP server protecting against unicode attacks, injection threats, and other AI vulnerabilities
npm Apache-2.0 -
cleaner-codegithub.com/goldmembrane/cleaner-codeupdated this year
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated code. Static analysis + CodeBERT deep learning. Runs locally.
npm MIT ★ 1 -
cleaner-codegithub.com/goldmembrane/cleaner-codeupdated this year
Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats.
npm ISC -
SKEPTIC — the local text forensics lab. Paste anything, trust nothing, transmit nothing. 9 deterministic instruments · zero dependencies · browser app + REST API + MCP server.
MIT -
Find hidden prompt-injection text: ASCII smuggling, zero-width/emoji stego, bidi, homoglyphs. One layer, not a full defense: it does not judge prompt injection written in plain, visible words.
MIT -
Prompt-injection scanner for AI agents: deterministic, documented rules (instruction override, jailbreaks, exfiltration URLs, tool hijack/MCP tool poisoning, hidden Unicode, encoded payloads) returning a risk score, categories and spans. Library + x402 pa
npm MIT -
Stop prompt injection in AI inbox triage and chat agents. Scans emails, web pages and messages for instructions aimed at the AI (hidden HTML, invisible Unicode, base64, fake system markers), fences untrusted content for the prompt, and gates the tool call
npm MIT -
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.
MIT ★ 4