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.
-
k11techlab-llm-assurance-toolkitgithub.com/K11-Software-Solutions/k11techlab-llm-assurance-toolkitactive
LLM red-teaming & assurance toolkit: 41 OWASP LLM Top 10 probes, CI quality gate, audit-ready HTML reports, Claude LLM-judge and an MCP server for agent-driven red-teaming.
pypi MIT ★ 2 -
mcp-security-toolkitgithub.com/x0base/mcp-security-toolkitupdated this year
13 atomic MCP tools for AppSec and AI Security: recon, MCP audit, prompt-injection audit, OWASP LLM Top 10
go MIT -
code-security-skillgithub.com/Chiehyii/code-security-skillupdated this year
Secure-coding knowledge base and MCP server for AI coding assistants, covering OWASP Top 10, ASVS, CWE, API, LLM, and supply-chain security.
-
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
npm MIT ★ 3 -
mcp-server-zapgithub.com/karacali/mcp-zapupdated this year
MCP server that exposes OWASP ZAP as tools to Claude and other LLM clients
pypi MIT -
meok-mcp-hardening-mcpgithub.com/csoai-org/meok-mcp-hardening-mcpupdated this year
MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10 (2025) + 5 MCP-specific risks to a 0-100 hardening score with HMAC-signed reports. By MEOK AI Labs.
pypi MIT -
MCP server on Cloudflare Workers giving AI agents least-privilege, human-approved access to Salesforce data. Threat model mapped to OWASP LLM Top 10 (2026), tested against a live agent.
-
mcp-api-pentestgithub.com/josenieto/mcp-api-logic-pentestupdated this year
MCP server for autonomous API logic penetration testing — OWASP API Top 10 / BOLA-IDOR detection via LLM-driven analysis
pypi 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 -
agent-sec-scannersgithub.com/AUAggy/agent-sec-scannersupdated this year
Security scanners for AI workloads on one shared audit engine. Home of bedrock-security-mcp (AWS Bedrock auditor, MCP + CLI) and @miaggy/core. Findings map to OWASP LLM Top 10, OWASP Agentic Top 10, NIST AI RMF, MITRE ATLAS.
npm -
OWASP LLM/Agent web search MCP server security exercise in TypeScript
-
Readiness checks for the code your AI writes: EU AI Act, GDPR, OWASP Top 10, OWASP LLM Top 10, CWE Top 25, EU Cyber Resilience Act. Runs locally. Not an audit or legal advice.
npm Apache-2.0 ★ 2 -
adversagithub.com/cognis-digital/adversaupdated this year
LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
NOASSERTION -
A from-scratch Model Context Protocol server (stdio, stdlib-only, zero deps): safe calc (OWASP LLM06), BM25 search, a no-LLM-judge answer grader, and live model-drift / eval-run lookups. 42 tests.
MIT ★ 1 -
gadriel-claude-pluginsgithub.com/Gadriel-ai/gadriel-claude-pluginsupdated this year
Gadriel AI Security Harness plugins for Claude Code — local SAST, SCA/SBOM, secrets & OWASP LLM security scanning via MCP.
-
Gadriel AI Security Harness for Claude Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner via MCP.
Apache-2.0 -
Gadriel AI Security Harness for OpenAI Codex — local MCP server and hooks for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 -
Gadriel AI Security Harness for Cursor — local MCP server, rules, and edit hooks for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
Apache-2.0 -
Gadriel AI Security Harness for VS Code — local SAST, SCA/SBOM, secrets, container, config & OWASP LLM security scanner and MCP server.
npm Apache-2.0 -
Gadriel AI Security Harness for GitHub Copilot — local MCP server, prompts, and instructions for SAST, SCA/SBOM, secrets & OWASP LLM security scanning.
npm Apache-2.0 ★ 2 -
Type-safe LLM vulnerability triage on Pydantic AI + MCP. Ten typed tools (NVD, OSV, KEV, EPSS, Exploit-DB, ATT&CK, SBOM, Nmap) ground a validated TriageReport with a deterministic SSVC verdict. Red-team battery (MITRE ATLAS), reproducible scorecard, OWASP LLM + ISO 42001 mapping. Next.js frontend.
MIT ★ 2 -
🔌 Exposes AI agent prompt injection firewall over MCP — OWASP LLM Top 10 1 runtime guard. MIT.
pypi MIT -
🔌 Exposes MEOK over MCP — Hardening MCP — automated security red-team for any MCP server. OWASP LLM Top 10 (2025) + 5 MCP-specific risks → 0-100 score + HMAC-signed report. By MEOK AI Labs.
MIT -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
Security check-up for APIs and AI agent tools: OWASP API Top 10 review of OpenAPI specs, headers, JWTs, release diffs and MCP tools, with fix code in 5 frameworks. Runs in the browser, the CLI and GitHub Actions.
MIT -
drheaderplus-mcpupdated this year
MCP server for DrHeaderPlus security header auditing
pypi MIT -
ai-security-mcpgithub.com/ai-security-scanner/ai-security-mcpupdated this year
Thin client MCP server for AI Security Scanner - connects to cloud-hosted 27 agents (100% OWASP coverage)
pypi MIT License -
garbleworksgithub.com/SamsonCyber/garbleworksupdated this year
Authorized LLM red-team harness: recipes, scoped fire, evolutionary search, Wilson ASR. MCP + API + TUI.
Apache-2.0 -
MCP server security auditor — tool poisoning, ASCII smuggling detection, prompt injection, OWASP Agentic Top 10. First OSS tool for MCP security.
AGPL-3.0 ★ 2 -
AIDEFEND MCP is a local-first AI Security Defensive Assistant that brings the full AIDEFEND countermeasure library into your environment and turns static knowledge into actionable protection for LLMs and agentic AI systems — privately, securely, and on-device.
MIT ★ 18 -
AI-powered security scanner for git repos — CLI, MCP, API, Web Dashboard, SDK with Cerebras LLM
npm Apache-2.0 -
hackmontygithub.com/dipankar/hackmontyupdated this year
Autonomous Sandbox Security Assessment
MIT -
Prompt-injection guardrail with a hardened LLM judge, guarded RAG and an MCP server · FastAPI + React/TS
MIT -
Educational reference AI agent and MCP server with an input guard, tool authorizer, output filter and audit logging, each control traced to OWASP, NIST or CSA guidance.
MIT -
AI Security Copilot for 2025 - MCP Server for comprehensive security analysis
npm MIT -
wazuh-mcpgithub.com/MoisesTapia/wazuh-mcpupdated this year
mcp for Wazuh
-
cerberusgithub.com/sreearunnishwar/cerberusupdated this year
Autonomous multi-agent security auditing platform with runtime exploit verification.
MIT -
mcp-for-code-quality-securitygithub.com/lgtkgtv/lgtkgtv-code_quality_security_tools_v4_mcp_agentstale
Python security scanner with Model Context Protocol (MCP) integration for AI assistants
pypi MIT License -
Agentguard-github.com/xAPT42/Agentguard-updated this year
Discover and govern your AI agent fleet automatic inventory with risk scoring
Apache-2.0 -
MCP gateway that safely exposes a double-entry payments ledger to an AI agent.
-
⚔️ Autonomous red-team swarm for AI apps, agents & MCP servers — pentest your agent before someone else does.
Apache-2.0 ★ 2 -
Adversarial Co-Generation Engine — concurrent Builder+Breaker agents for production-grade AI code security
pypi MIT ★ 1 -
aegisq-codeshield-mcpgithub.com/jeffgrayson1969/aegisq-codeshieldupdated this year
AegisQ-CodeShield MCP server — AI security scanning for Claude Code, Cursor, Windsurf, Copilot, ChatGPT, Cline, and more
npm MIT -
Defensive web-security auditor for applications you own: an LLM agent in a Docker sandbox, a scope guard, CVSS 3.1 findings, CI mode and an MCP server.
MIT -
ThreatModelgithub.com/UnitOneAI/ThreatModelupdated this year
Open-source, MCP-first threat modeling that proposes and sandbox-validates the fix — not just the report. Apache-2.0."
Apache-2.0 -
mcp-api-pentestgithub.com/josenieto/mcp-api-pentestupdated this year
MCP server for autonomous API logic penetration testing. AI-driven detection of OWASP API Top 10 vulnerabilities (BOLA/IDOR) via multi-session authorization comparison. Supports Bearer, Basic, API Key, Cookie auth. Generates Markdown security audit reports with evidence.
MIT ★ 1 -
A framework for building and running your own living GenAI/LLM threat model. Ships with a curated reference catalog, an LLM-driven assessor, and an MCP server
Apache-2.0 ★ 2 -
mcp-servergithub.com/middleBrick/mcp-serverupdated this year
MCP server for middleBrick API security scanning — scan APIs for vulnerabilities from Claude, Cursor, or any MCP-compatible AI tool
npm Apache-2.0 -
Security rules for AI coding agents: 681 rules, 21 platforms, MCP server, Claude Code plugin. Web, mobile, databases, cloud, AI, banking.
MIT -
Give AI agents a safe, self-hosted ZAP operator for guided web security scans, findings, reports, and production guardrails.
oci Apache-2.0 ★ 70 -
pluto-aguardgithub.com/arshan846/pluto-aguardupdated this year
Security scanner and launch gate for AI agents & MCP apps — config scanning, policy coverage, risk modeling, drift detection, CI/SARIF, and launch-readiness evidence
Apache-2.0 ★ 4 -
One scored audit of everything you ship: code, sites, apps, APIs, containers, IaC, cloud and mobile. CLI, CI and MCP for AI agents.
npm MIT ★ 1 -
Attack. Defend. Verify. Red-team your AI agents, enforce zero-trust policy at runtime, and prove each fix holds in CI. Includes an MCP proxy.
NOASSERTION -
Agentic API testing and security validation: AI agents that act only through a permission-gated, SSRF-guarded, audited MCP tool layer.
NOASSERTION -
Agentic API testing and security validation: AI agents that act only through a permission-gated, SSRF-guarded, audited MCP tool layer.
NOASSERTION -
openagentontologygithub.com/cwnapps/openagentontologyupdated this year
Auto-generate a governance ontology, Trust Profile, and signed badge for any agent, MCP server, repo, OpenAPI, Rego, or workflow. The OpenTelemetry for agent governance.
pypi Apache-2.0 -
MCP server that gives local LLMs (LM Studio, Ollama) live web access plus recon, OSINT, and authorized security-testing tools like Burp/ZAP/Wapiti integration, APK triage, and self-extending skills, all safety-gated by default.
MIT ★ 3 -
shieldpi-mcpgithub.com/shieldpi1/shieldpi-watchtowerupdated this year
MCP server for ShieldPi Watchtower — run LLM security scans, generate drop-in guardrails from scan findings, operate the AI SOC analyst (incident triage + kill-chain reconstruction), and query the live agent monitor from Claude Desktop / Cursor / Continue.
pypi MIT -
AISRF, the AI Security & Research Framework: every LLM request from your apps and agents becomes a ticket a human approves before it reaches the backend. Analyzers, guardrails (Rebuff, LLM Guard, NeMo, Lakera), red teaming (garak, promptfoo, PyRIT), source code review, reports, MCP server.
Apache-2.0 ★ 2 -
Autonomous, single-file AI multi-agent utility coordinating System Architect, Coder, and Security Auditor sub-agents locally using Google Gemini & SQLAlchemy.
MIT