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.
-
Threat models for developers: a plain-language file in your repo, a CLI, an MCP server for agents, and a serverless web app
Apache-2.0 -
iriusrisk-cligithub.com/iriusrisk/iriusrisk_cliupdated this year
AI-powered threat modeling integration for IriusRisk. Command line interface and MCP server for security analysis.
pypi MIT License -
AI-maintained security annotations for code. Continuous threat modeling, enforced in CI.
npm MIT ★ 22 -
Model Context Protocol (MCP) server in Go for ThreatBook TDP (微步在线威胁检测平台): 105 OpenAPI endpoints + 4 diagnostics as typed MCP tools - alert triage, incident forensics, log hunting, threat intel & SOC automation.
MIT ★ 2 -
MCP server that draws CORAS risk and threat diagrams for the SINTEF Threat Modelling Tool (bundled). Describe a risk picture in words, get a .dgx the 2007 editor opens natively.
npm MIT -
Agent-powered red team testing workbench with asset mapping, threat modeling, multi-agent workflows, cloud assessment, reports and MCP.
MIT ★ 49 -
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 -
threatmod-aigithub.com/cintelis/threatmod-aiupdated this year
AI-powered security threat modelling pipeline — STRIDE analysis via LLM, AWS control verification via MCP, two-stage approval workflow, GitHub + Confluence publication.
MIT -
honeymcpgithub.com/kosiorkosa47/honeymcpupdated this year
Open-source honeypot for MCP (Model Context Protocol) servers. Collects threat intel on attacks against the AI agent ecosystem.
NOASSERTION ★ 3 -
Autonomous Cyber Threat Neutralization Platform powered by LangGraph Agentic AI, Model Context Protocol (MCP), and Sandboxed Docker Execution.
-
Enterprise-grade Model Context Protocol (MCP) server for Splunk with 100 tools for search, SOC operations, threat hunting, knowledge management, and cluster diagnostics.
NOASSERTION -
Filescan.io MCP server - Rust implementation for file/URL scanning, report search, reputation checks, and threat intelligence via Model Context Protocol
★ 1 -
An open-source, AI-native Model Context Protocol (MCP) server bridging Large Language Models with core network diagnostic tools for automated observability, threat detection, and agentic security orchestration
★ 1 -
Self-hosted telemetry guardian: ingests browser-console activity, scores it with a language model for insider-threat and data-exfiltration signals, and persists sessions, events and risk assessments in MongoDB via an MCP server. Experimental, not production ready.
Apache-2.0 -
Model Context Protocol (MCP) server providing comprehensive cybersecurity intelligence from HUMAN Security. Offers real-time attack monitoring, threat detection, fraud prevention, PCI DSS compliance validation, and supply chain security for AI-powered app
npm MIT -
Model Context Protocol (MCP) server providing comprehensive cybersecurity intelligence from HUMAN Security. Offers real-time attack monitoring, threat detection, fraud prevention, PCI DSS compliance validation, and supply chain security for AI-powered app
npm MIT -
castellangithub.com/cognis-digital/castellanupdated this year
🏰 castellan — the keeper of your threat model. Offline, MCP-native threat modeling: STRIDE + LINDDUN, DREAD risk, attack trees & 625 compliance frameworks, from a spec or your IaC.
NOASSERTION -
MCP server for PyTM-based threat modeling.
-
AI threat-modelling tools: architecture in, ATLAS out.
npm Apache-2.0 -
MCP server for Mipiti — security posture platform. Connect AI coding agents to threat modeling, controls, and compliance.
pypi NOASSERTION ★ 1 -
Defense/Aerospace domain intelligence MCP for compliance and threat modeling
npm MIT -
security-mcpgithub.com/tzervas/security-mcpupdated this year
MCP (Model Context Protocol) server providing security screening, injection detection, and threat analysis
cargo MIT -
opencti-mcp-servergithub.com/blauwers/opencti-mcp-serverupdated this year
The OpenCTI MCP server exposes OpenCTI threat-intelligence operations through the Model Context Protocol (MCP).
NOASSERTION ★ 1 -
A Model Context Protocol (MCP) server providing threat intelligence tools to help AI assistants with security investigations and analysis.
MIT ★ 1 -
A Model Context Protocol (MCP) server that integrates with the MISP (Malware Information Sharing Platform) to provide threat intelligence capabilities to Large Language Models.
★ 13 -
mcp-security-toolkitgithub.com/JAvito-GC/mcp-security-toolkitupdated this year
Model Context Protocol servers for security operations: SIEM, Identity, Ticketing, Threat Intel, Cloud
MIT -
alphaMountain-MCPgithub.com/ZuuuSSzz/alphaMountain-MCPupdated this year
An MCP (Model Context Protocol) server for the (https://alphamountain.ai) API, providing threat intelligence, URL categorization, and domain intelligence tools.
-
brand-narrative-intelligence-mcpgithub.com/apifyforge/brand-narrative-intelligence-mcpupdated this year
Brand narrative intelligence and brand threat detection for AI agents via the Model Context Protocol.
MIT -
thinking-toolsgithub.com/PranayMahendrakar/thinking-toolsupdated this year
Five rigorous reasoning protocols - debate, red team, argument audit, threat model, study sanity. Free MCP plugin for Claude and ChatGPT, zero extra credits.
MIT -
Hierarchical pest and disease modeling framework for AgStack (Linux Foundation). 13 models, 19 crops, 54 threats. Python wheel + FastAPI + MCP server.
Apache-2.0 ★ 1 -
Enterprise autonomous phishing triage and SOC automation platform combining LLMs with the Model Context Protocol (MCP) for SIEM/EDR log correlation and threat hunting.
-
mcp-n8n-security-scannergithub.com/smakarim/mcp-n8n-security-scannerupdated this year
MCP server that statically scans n8n automation workflows for security issues (SAST for n8n): SSRF/IMDS, code injection, unauth webhooks, hardcoded secrets, PII egress. Includes STRIDE threat model.
MIT -
security-framework-mcpgithub.com/zer0-kr/security-framework-mcpupdated this year
Unified NIST + OWASP security framework MCP server — 36 tools, 3439+ records, live NVD/KEV, PDF reading, STRIDE threat modeling, compliance mapping
MIT ★ 14 -
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.
-
AegisGate MCP — Standalone Model Context Protocol security server with 23 security layers, vendored ONNX runtime, neural threat detection (L3). SSE streaming. Session management. Zero module dependencies. Multi-arch (amd64/arm64). Apache 2.0.
oci Apache-2.0 -
Forward-deployed engineering in public: a role-scoped MCP server with prompt-injection defenses, 173 tests, and an eval harness (45.9% to 94.6% safe decisions). Live dashboard + threat model + ADRs.
-
MCP server for the Guard ecosystem — config validation, docs search and live threat detection for fastapi-guard, guard-core and guard-agent. Answers from the versions installed in your project, not from a model's memory.
pypi MIT ★ 3 -
🛡️ Autonomous Multi-Agent Threat Hunting & Incident Response Swarm engineered with AutoGen, Azure Sentinel, and Model Context Protocol (MCP). Sub-second Netfilter isolation & real-time KQL hunting analytics.
MIT ★ 1 -
A comprehensive Model Context Protocol (MCP) server for analyzing SonicWall firewall logs from SonicOS 7.x and 8.x. This server provides intelligent log analysis, threat detection, and security insights through a fully MCP-compliant interface using SSE/HTTP transport.
MIT ★ 8 -
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 server to give Claude a headless browser. It includes OAuth 2.1 for security and checks for prompt injection attempts. Every render request goes through a DNS pinned egress proxy, and the project comes with a documented threat model.
MIT ★ 4 -
pharma-pipeline-intelligence-mcpgithub.com/apifyforge/pharma-pipeline-intelligence-mcpupdated this year
Drug pipeline competitive intelligence for pharmaceutical companies, biotech investors, and medical affairs teams starts here. This MCP server orchestrates **7 live data sources** — ClinicalTrials.gov, FDA, EMA, USPTO, and PubMed — to produce a composite **Pipeline Threat Score (0-100)** with four specialized sub-models.
MIT ★ 1 -
Ironheights: The Immune System for AI Agents. Protects any AI bot that installs it: scans agent skills (OpenClaw, Claude, Grok Bot, Codex, Cursor, MCP) A-F, threat-model PR checks, MCP server, drift guard, posture report. Local, no telemetry.
npm Apache-2.0 ★ 4 -
Claude Code security plugin and agentskills.io skill pack for securing LLM agents: threat modelling, config audits, prompt injection review, MCP server review, incident lookup, security evals, Semgrep rules, guard hooks and an incident-database MCP server.
MIT -
dingdawg-shieldgithub.com/dingdawg/dingdawg-shieldupdated this year
Governance receipts for AI agents — AI-driven security scanning with a stack-specific threat model, signed audit receipts for every scan, and trust scores that improve with verified fixes. Supports EU AI Act, Colorado AI Act (SB 24-205), and NIST AI RMF a
npm BUSL-1.1 -
threat-intel-mcpstale
Official MCP server for FalconFeeds.io threat intelligence data
npm ISC -
Official MCP server for FalconFeeds.io threat intelligence data
npm ISC -
VirusTotal MCP Server是一个让AI结合威胁情报进行深入分析、基于 Model Context Protocol (MCP) 开发的 VirusTotal API 调用工具,为用户提供文件、IP地址、域名和URL的威胁情报查询功能,并将得到的数据喂给AI进行二次分析,提升威胁情报分析能力并给予处置建议。
MIT ★ 10 -
neuromorphic-threat-intelligence-mcpgithub.com/apifyforge/neuromorphic-threat-intelligence-mcpupdated this year
Neuromorphic threat intelligence for AI agents — this MCP server applies **8 brain-inspired and mathematical frameworks** to cyber threat detection, pulling live data from **15 sources** spanning vulnerability databases, internet scanning infrastructure, sanctions registries, social signals, and code repositories.
MIT -
A 135+ tool DFIR toolkit, a live self-updating threat-intel platform, and a 332-tool MCP server — on one Cloudflare Workers deploy. MIT licensed. Portfolio: pranithjain.qzz.io
★ 8 -
falconfeeds-mcpstale
Official MCP server for FalconFeeds.io threat intelligence data
npm ISC -
gti-mcp-standalonegithub.com/googleSandy/gti-mcp-standaloneupdated this year
—
NOASSERTION ★ 4 -
secops-agent-triagegithub.com/drummer475-94/secops-agent-triageupdated this year
Tool-calling SOC triage agent with multi-format alert ingestion, threat-intelligence enrichment, and structured NIST/MITRE assessments.
MIT -
MCP server for the MITRE ATT&CK knowledge base: map alerts to techniques, profile threat groups, analyze detection coverage, and enrich SOC workflows from an AI client.
npm MIT ★ 4 -
MCP server for the F6 Threat Intelligence API
pypi Apache-2.0 -
@iflow-mcp/cyreslab-ai-urlhaus-mcp-servergithub.com/iflow-mcp/cyreslab-ai-urlhaus-mcp-serverupdated this year
MCP server for accessing URLhaus malicious URL database from abuse.ch - provides threat intelligence for cybersecurity research
npm MIT -
MISP Threat Intelligence Platform MCP Server
npm Apache-2.0 -
Official MCP server for Threadlinqs Intelligence — 81 tools and 25 analyst-playbook prompts for threat intel, detections (Sigma/SPL/KQL/CQL), IOCs, actors, C2, MITRE chains, correlations and CVE/CWE. npm: intelthreadlinqs-mcp
npm MIT -
Read-only MCP server for HEARTH, the community threat hunting hypothesis library
npm MIT -
MCP server exposing the OpenCTI threat-intelligence platform to AI assistants.
pypi MIT