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.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Security MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/topic/security/page/2

Verdicts · 119 servers

✓SAFE31!CAUTION21✕BLOCK67

Transports

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

25–48 of 119 · ranked by trust score, then stars

Model Context Provider

allsmog/mcp-pentest

✓SAFE B

MCP server for authorized pentest workflows: Nmap/Gobuster orchestration, context aggregation, AI-assisted triage, and reporting.

★ 231 destructivestdio

ed-dryha-reolink

ed-dryha/reolink-mcp

✓SAFE B

An open-source MCP (Model Context Protocol) server for Reolink cameras: lets Claude — or any MCP client — see and control Reolink cameras on the local network.

★ 2Not listed in sourcestdio

forcedream

forcedreamai/forcedream-mcp

✓SAFE B

MCP server for ForceDream — discover, invoke, and trustlessly verify AI agents with cryptographic proofs.

★ 11 writestdio

airlock-rls-mcp

mateuszingano/airlock-rls-mcp

✓SAFE B

MCP server: let Cursor / Claude Code check a Supabase app for an exposed service_role key and broken RLS while it builds it

★ 02 read

attestd-mcp

attestd-io/attestd-mcp

✓SAFE B

Official MCP server for Attestd. Use Attestd supply chain and CVE signals directly in Claude Code, Cursor, and Windsurf.

★ 0Not listed in sourcestdio

beepboop2025-data-breach-detector

beepboop2025/data-breach-detector

✓SAFE B

Read-only breach intelligence for defenders: exposure checks, breach news, and threat assessment over MCP. Never leaked records.

★ 0Not listed in sourcestdio

fino

tophole-alphabetizer167/fino

✓SAFE B

Track personal finances locally with AI, connect bank accounts, analyze spending, and chat with Claude while keeping data on your machine

★ 02 destructivestdio

linkedin-osint-cli

gnmike57/linkedin-osint-cli

!CAUTION B

LinkedIn CLI + MCP server: 43 platform commands plus a 13-command OSINT suite (company discovery, employee scraping, username generation, role classification, org charts). Interactive console, cookie-session auth, AI-agent native.

★ 01 readstdio

selflabbs-security-intel

datakoot/security-intel-mcp

✓SAFE B

Vulnerability-intelligence MCP server for AI agents: CVE lookups (NVD) and dependency-manifest audits (OSV). Keyless.

★ 04 readstreamable-http

seosiri-api-guard-mcp-server

SEOSiri-Official/seosiri-api-guard-mcp-server

✓SAFE B

A sovereign, universal API validation and multi-industry compliance security MCP server supporting OWASP, HIPAA, PCI-DSS, GDPR, and SEO/AEO metadata guardrails.

★ 01 readsse

mcp-tenant-isolation

subodhkc/mcp-tenant-isolation

!CAUTION B

Static analysis scanner for multi-tenant SaaS and MCP server code. 57 deterministic rules for cross-tenant data leakage, IDOR, RLS, and MCP-specific risks. Includes MCP server, SARIF output, and GitHub Action.

★ 45 readstdio

SonarQube

sonarsource/sonarqube-mcp-server

!CAUTION B

Official SonarQube MCP Server for code quality and security in AI agents

★ 655Not listed in sourcestdio

llamator-mcp-server

kyle122497/llamator-mcp-server

!CAUTION B

🚀 Automate LLM red teaming workflows with the MCP server for LLAMATOR, featuring asynchronous job handling and seamless integration.

★ 22 writestreamable-http

ghidra-mcp

bethington/ghidra-mcp

!CAUTION B

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.

★ 4,8993 readstdio

GitGuardian

gitguardian/ggmcp

!CAUTION B

MCP server for remediating hardcoded secrets using GitGuardian’s API. It detects over 600 secret types and prevents credential leaks before code is made public.

★ 362 writestdio

GitGuardian

gitguardian/gg-mcp

!CAUTION B

MCP server for remediating hardcoded secrets using GitGuardian’s API. It detects over 600 secret types and prevents credential leaks before code is made public.

★ 362 writestdio

Security Tools

cyproxio/mcp-for-security

!CAUTION B

MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.

★ 6291 destructivestdio

echelongraph-mcp

echelongraph/echelongraph-mcp

!CAUTION B

MCP server for CVE intelligence: 16 read-only tools for CVE records, CISA KEV, EPSS history, exploits, fix guidance as sources state it, version, SBOM and lockfile checks, vendor advisories, and per-CVE exposure from Shodan data (© Shodan). Free and keyless.

★ 213 readstdio

rustpanosmcp

mechubsec/rustpanosmcp

✓SAFE B

Async Rust MCP server for Palo Alto Networks PAN-OS firewalls — bearer-token auth, per-token device/tool scopes, guarded candidate-config lifecycle

★ 1Not listed in sourcestdio

Ghidra

bethington/ghidra-mcp

!CAUTION B

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.

★ 3,9483 readstdio

Fast ThreatIntel

4r9un/fastmcp-threatintel

!CAUTION B

AI-Powered Threat Intelligence MCP tool

★ 401 read

webcrypt

putervision/webcrypt

!CAUTION C

Zero-dependency Web Crypto suite & Model Context Protocol (MCP) server for AES-256-GCM, RSA-4096, and AI agent security.

★ 153 writestdio

MiMo Free API

fu-jie/mimo-free-api-mcp

!CAUTION C

MiMo Free API MCP: 基于官网逆向的高性能 OpenAI / HTTP MCP 代理网关。支持搜索、识图、长文本分段及 SQLite 持久化。

★ 292 readstreamable-http

OpenOSINT

openosint/openosint

!CAUTION C

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 20 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

★ 1,63110 readstdio

Other jobs

By risk

Questions

How do you decide which servers are security servers?
By the categories each server's own repository declares, mapped onto this job by a hand-kept table. A server can belong to more than one job, and one whose repository declares no matching category is not listed here.
Which security MCP servers rank highest on trust?
Agentic Radar (splx-ai/agentic-radar), Kali Connector (wh0am123/mcp-kali-server) and Security Hub (fuzzinglabs/mcp-security-hub), by trust score and then stars. Ranking never uses popularity to change a verdict.
How many security servers only read?
35 of the 119 declare tools that all only read; 26 expose at least one destructive tool.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.