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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
PromptGuard Scan remote MCP documentation for prompt injection and LLM security testing.
NOASSERTION -
prompt-injection-mcpgithub.com/Xiangyu-Li97/prompt-injection-mcpupdated this year
MCP Server for authorized AI security research and penetration testing (Educational purposes only - requires explicit authorization)
NOASSERTION ★ 3 -
Prompt injection scanner for documents, web pages and RAG content: instruction overrides, spoofed chat roles, hidden text and data-exfiltration attempts, as a CLI and an MCP server
npm MIT -
Prompt injection against a SOC triage agent that uses retrieval, memory and skills — and three layered defenses, as a live demo and an MCP server.
MIT -
@mukundakatta/prompt-injection-shield-mcpgithub.com/mukundakatta/prompt-injection-shield-mcpupdated this year
MCP server exposing prompt-injection-shield: scan untrusted text for prompt-injection signals, score risk, strip dangerous lines. Built for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
npm 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 -
🔌 Exposes AI agent prompt injection firewall over MCP — OWASP LLM Top 10 1 runtime guard. MIT.
pypi MIT -
mcp-injection-guardgithub.com/Hosein-Abdollahi/mcp-injection-guardupdated this year
MCP server that blocks indirect prompt injection by tracking data provenance, not text patterns.
MIT ★ 1 -
injection-pii-guardrail-mcpgithub.com/ss-2303/agent-guardrail-mcpupdated this year
An MCP server providing prompt-injection detection, PII/secrets redaction, and an audit trail for AI agents.
pypi MIT -
MCP server and CLI that scan untrusted content for prompt-injection patterns before it reaches your agent - offline, explainable, cross-agent.
MIT ★ 1 -
A Local-First, Zero-Cost Prompt Injection Detection Server for the Model Context Protocol.
pypi MIT -
Pattern-based prompt-injection and jailbreak screening with optional semantic analysis.
npm MIT -
Deterministic security gateway & remote MCP server for autonomous AI commerce — 12 policy rules blocking prompt-injected purchases with zero financial leak
MIT ★ 2 -
Prompt-injection guardrail with a hardened LLM judge, guarded RAG and an MCP server · FastAPI + React/TS
MIT -
malskannergithub.com/Octolabo/malskannerupdated this year
Scan a repo for hidden prompt-injection before your AI agent trusts it — CLI, MCP server & GitHub Action. Run: npx malskanner <repo>. 0 false positives across 5,620 files.
MIT ★ 5 -
Local MCP server for the lovec.tech prompt-injection detector — check_prompt_injection tool for Claude Desktop/Code and other MCP clients
pypi Apache-2.0 -
Deterministic prompt injection classification, secret entropy detection, PII redacting, and synthetic dataset bias auditing.
MIT -
MCP server: scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them (17 languages).
MIT -
rmorgithub.com/jimbarritt/rmorupdated this year
Secure web fetch MCP server with prompt injection detection
cargo MIT -
mcp-safe-fetchgithub.com/PortfolioKB/mcp-safe-fetchupdated this year
An injection-aware content fetcher exposed over MCP: layered prompt-injection sanitization and a resolve-and-classify SSRF guard.
MIT -
A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain.
npm MIT -
hermes-shieldgithub.com/amurlaniakea/hermes-shieldupdated this year
Input sanitizer for AI agents — anti-prompt-injection shield
AGPL-3.0 ★ 1 -
agentguard-mcpupdated this year
AgentGuard MCP server — scans Cursor tool responses for prompt injection and PII leaks
npm MIT -
MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026 Anthropic MCP RCE class, mcp-server-git CVE chain, DockerDash injection chain, OWASP LLM Top 10 + GenAI Red Team v1. Scans live MCP /tools/list endpoints OR pasted JSON. Free 5/day, Pro £29/mo for unlimited + signed safety reports auditors and procurement accept. By MEOK AI Labs.
pypi MIT License -
Honeypot MCP server and canary tokens for detecting compromised or prompt-injected AI agents
npm MIT -
@injectshield/mcpgithub.com/bch1212/injectshieldupdated this year
MCP server for InjectShield — prompt-injection firewall for AI agents.
npm MIT -
decoy-mcpgithub.com/decoy-run/decoy-mcpupdated this year
Security tripwires for AI agents. Detect prompt injection in real time.
npm 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 -
Security-tooling MCP server with SSRF guards, prompt-injection containment and a hash-chained audit log
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 -
mcp-sandbox-scaupdated this year
MCP server that scans repos and AI tools for prompt injections, exfiltration, and malicious behavior
npm MIT -
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit
MIT ★ 2 -
koma-gate-mcpgithub.com/swnotmetal/project-komaupdated this year
MCP server exposing Koma Gate prompt-injection classification as a tool for AI agents.
npm MIT -
@exfil/canarygithub.com/exfil-hq/canaryupdated this year
Transparent MCP proxy that watermarks agent tool responses and blocks data exfiltration caused by prompt injection.
npm MIT -
Stop prompt injection in AI inbox and chat agents: scan emails, pages and messages for instructions aimed at the AI, fence untrusted content for the prompt, and gate the tool calls an agent makes after reading it. CLI, library, MCP server. Zero dependencies.
npm MIT -
Self-hosted MCP server for Grok Bot to post and reply on X, with prompt-injection defenses
MIT -
Secure MCP server for AI-assisted PCAP analysis with tshark, redaction and prompt-injection defense.
MIT -
Read-only WhatsApp MCP server designed against prompt injection: no send, network blocked, audit log, chat exclusions
MIT -
security-mcpgithub.com/yeodh10/security-mcpupdated this year
An MCP server exposing security tools (prompt-injection scan + CVE lookup/version-impact) that Claude calls directly. FastMCP, reuses cve-radar/prompt-guard logic.
-
MCP server for Moodle with SSO login, server-side prompt-injection defenses and Obsidian sync
pypi MIT ★ 2 -
guardianshieldgithub.com/sparkvibe-io/guardianshieldupdated this year
Universal AI security layer - MCP server for code scanning, PII detection, prompt injection defense, secret detection, and audit logging
pypi Apache-2.0 -
@muhannad-hash/mcp-shieldgithub.com/muhannad-hash/mcp-shieldupdated this year
MCP server that scans other MCP servers for backdoors, prompt injection, exfiltration, and supply chain risks
npm MIT -
Security auditor for AI agents and MCP servers — config analysis, prompt injection testing, tool probing, data flow tracing
npm MIT -
LLM Security Gateway — AI application firewall, prompt injection risk analysis & sovereign audit runtime.
Apache-2.0 -
MCP server providing secure file operations with prompt injection detection, API key validation, and audit logging
-
Klar: prompt injection protection for AI agents. Claude Code and Codex plugin, MCP server and CLI.
MIT ★ 1 -
mcp-server-fetch-tomupdated this year
A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs, with prompt injection safeguards
pypi MIT -
sentricore-agent-securitygithub.com/Pothan0/sentricore-agent-securityupdated this year
Security gateway for AI agents on REST and MCP: prompt-injection defense, tool governance, human-in-the-loop escalation, tamper-evident audit logs.
-
webmcp-scannergithub.com/ElonMusk2002/webmcp-scannerupdated this year
Chrome extension that discovers WebMCP tools on a page and flags IDOR, prompt injection, missing consent gates, and over-broad schemas.
-
An arcade game about a prompt-injection worm loose in a swarm of AI agents. Humans play with a blade; agents play over MCP.
MIT -
Content moderation with prompt injection detection, toxicity scoring, and PII redaction
npm MIT -
AI agent that manages GitHub through an MCP server and asks a human before any write. Built to explore prompt injection.
-
A firewall for LLM traffic: detect prompt injection, jailbreaks, and secret/PII leaks. Zero-dependency Python library + CLI + MCP server.
MIT ★ 1 -
@safekeylab/mcp-servergithub.com/safekeylab/mcp-serverupdated this year
MCP (Model Context Protocol) server for SafeKeyLab AI security tools - PII scanning, prompt injection detection, and model security analysis
npm MIT -
@codesentrix/mcpactive
Code Sentrix MCP Server - AI Security, AgentShield Anti-Prompt Injection, and Quality Gates for Cursor, Claude, Antigravity, and Windsurf
npm Apache-2.0 -
Safety checks for AI agents: package, command, prompt-injection, domain and code audits via MCP.
pypi MIT -
kaggle-mcpgithub.com/parkseokjune/kaggle-mcpupdated this year
Safety-first MCP server connecting Claude to Kaggle (competitions, datasets, kernels, models) — confirm-token gates, submission budget, prompt-injection hardening.
pypi MIT -
Testing AI-facing APIs: an own MCP server and an LLM endpoint on Claude with evals, groundedness and prompt-injection checks
MIT -
GuardXgithub.com/ai-craftsman404/GuardXupdated this year
LLM security scanner for Claude Code, with MCP-based testing for prompt injection, RAG risks, and supply-chain exposure.
MIT -
An MCP server over a synthetic payments sandbox, with a support agent, signed human approvals for refunds, prompt-injection guardrails and an offline eval suite
Apache-2.0