MCP servers · by job
Security MCP servers
119 MCP servers that scan, test and investigate security issues. 31 are SAFE, 21 CAUTION and 67 BLOCK. Ranked by trust score; each card opens the full audit.
Cite
Cite this page
ModelsAtlas. “Security MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/topic/security/page/3
Verdicts · 119 servers
Transports
- stdio, runs locally89
- Streamable HTTP, remote49
- SSE, legacy remote9
- Not declared18
A server can list more than one transport.
Tool risk
26
servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 14 tools.
Servers with no destructive tools →119 security servers
49–72 of 119 · ranked by trust score, then stars
Ethereum Wallet Toolkit
nirholas/ethereum-wallet-toolkit
Python toolkit for Ethereum wallets: CLI tools + Model Context Protocol (MCP) servers for wallet generation, BIP39/BIP44 HD wallets, Web3 Secret Storage V3 keystores, and EIP-712 typed data signing
windbg-mcp
glslang/windbg-mcp
MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --listen
LitterBox
blacksnufkin/litterbox
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
mcp-security
google/mcp-security
Jeb
dawnslab/jebmcp
Jebmcp
flankerhqd/jebmcp
Ida Pro Server
fdrechsler/mcp-server-idapro
A Model Context Protocol (MCP) server that enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis tasks.
Pentester
halilkirazkaya/pentester-mcp
Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via the Model Context Protocol (MCP) using a secure Docker sandbox.
Cortex
gambletan/cortex
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory.
rustjunosmcp
fastrevmd-lab/rustjunosmcp
MCP server for Juniper Junos devices, built on rustnetconf.
rustjunosmcp
mechubsec/rustjunosmcp
MCP server for Juniper Junos devices, built on rustnetconf.
aga-mcp-server
attestedintelligence/aga-mcp-server
Signed decision records for agent vendors facing customer evidence reviews. Public reference gateway and static verifier; pre-pilot, with documented limits.
armadoc-cli
waimun/armadoc-cli
Local MCP server and CLI for Armadoc. Lets your AI agent send and read end-to-end encrypted documents; your private key and plaintext never leave your machine.
awesome-ai-red-teaming-jp
Ajay77187718/awesome-ai-red-teaming-jp
整理された日本語のAIレッドチーミング情報集。攻撃手法、ツール、規制、防御、論文をまとめて学べるリソース集
mcprobe
Amalleheavy908/mcprobe
Validate MCP servers by inspecting tools, schemas, and resource URIs to identify security risks before connection.
ratchet
suhui-organization/ratchet
Compile a least-privilege policy from what your AI agents can actually reach - then hand over evidence the recipient verifies without trusting you.
Compartment
maxfreedompollard/compartment
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
Zettelforge
rolandpg/zettelforge
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
ZettelForge
threatrecall/zettelforge
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
rustsdcmcp
mechubsec/rustsdcmcp
Async Rust MCP server for HPE Juniper Security Director Cloud — a mechub project
MindForge
opok-ops/MindForge
Production-grade lifelong memory for AI agents — 4-tier memory, knowledge graph, E2EE, federated P2P, MCP server.
Hammer
praetorian-inc/mcphammer
MCP security testing framework for evaluating Model Context Protocol server vulnerabilities
yorishiro-proxy
usk6666/yorishiro-proxy
AI-native MITM proxy — MCP server for traffic interception, recording & replay
Reverse Engineer Anything
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Other jobs
By risk
Questions
How do you decide which servers are security servers?
Which security MCP servers rank highest on trust?
How many security servers only read?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- How do you decide which servers are security servers?
- Which security MCP servers rank highest on trust?
- How many security servers only read?