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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
Open source LNG plant cyber range for Qatar: live process simulation, IEC 62443 controls, MITRE ATT&CK for ICS attack paths, NCSA incident playbooks and an MCP server.
MIT ★ 1 -
Turn your AI into a penetration tester with a security MCP server for offensive testing and attack simulation
-
oraclewatchgithub.com/cognis-digital/oraclewatchupdated this year
Monitors price-oracle feeds for staleness, deviation, and manipulation exposure, simulating TWAP/spot attack profitability per pool.
NOASSERTION -
MCP server: Cisco Foundation-Sec-8B detects and blocks SDN attacks with simulated, auto-rolled-back policy (IOS-XE RESTCONF/NETCONF)
Apache-2.0 -
Sovereign debt crisis modeling for AI agents and LLM workflows — this MCP server delivers eight academically-grounded simulation tools spanning default dynamics, contagion networks, fiscal sustainability, restructuring design, speculative attacks, and political regime transitions.
MIT -
Autonomous cyber red team intelligence for AI agents — this MCP server gives Claude, GPT-4o, and any MCP-compatible agent the ability to run quantitative attack simulations, synthesize exploit chains, forecast vulnerability emergence, and model adversary behavior using eight rigorously implemented mathematical frameworks.
MIT ★ 1 -
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.
pypi MIT -
cymulate-mcp-toolsgithub.com/lyonzin/cymulate-mcp-toolsupdated this year
Community MCP for Cymulate — 100% API coverage (337 endpoints) via 106 tools. BAS, Exposure Validation, ASM, Purple Team. STDIO + HTTP transport.
MIT -
SpectreWeb-AIgithub.com/tuannguyen14/SpectreWeb-AIupdated this year
Self-Learning AI for Manual Web Penetration Testing
★ 14 -
Dirgithub.com/SiteQ8/Diractive
An open source seawater desalination plant cyber range for Saudi Arabia, aligned to the NCA OTCC, with a live process simulation, MITRE ATT&CK for ICS scenarios and an MCP server.
MIT