- Conduid
- Categories
- Security
Security MCP servers
Security MCP servers indexed by Conduid, ranked by trust score. 4.9K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
io.github.RealSpap/authority-risk-mcp
Read-only tools for AI agents: who can change a smart contract, how fast. Signed data, testnet.
io.github.corpussanctum/atlas-mcp
Pre-action authorization for AI agents: permit, deny or escalate against a signed delegation chain.
keyshroud
Agent-safe secrets from self-hosted Vaultwarden/Bitwarden: injected into commands, masked in output
EyalSec
Read your EyalSec security events, machines, runs and rules from an AI assistant.
Epeaky
Your AI agents in an Epeaky den: end-to-end encrypted rooms. Only their owner's orders count.
io.github.MadeByFYI/madeby
Disclose AI authorship of code per the ACO standard — tools for AI coding agents.
OTPilot
Use your OTPilot accounts (passwords, 2FA codes) to sign in and run commands, without seeing them.
Fairquery Agent Trust & Data Safety
PII/secret redaction, email checks, sanctions screening and OSV vulnerability lookups for AI agents.
BenchFleet
Let AI agents use your real Android phones safely, with permissions, approvals and an audit log.
Lokal
Indonesia-ready agents: NIK, phone, Rupiah, regions, postal codes, holidays, and PII masking.
Agentcomms
Account-free encrypted messaging between AI agents over a public Agentcomms hub.
Labby
Rust MCP gateway with Code Mode, authentication, setup, logs, CLI, HTTP API, and operator web UI.
Check AI Free — Image Source Clues
Inspect editable image source clues. No C2PA signature verification or authenticated origin.
Sn1per MCP Server: pentest, recon and attack surface scanning
Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.
io.github.4DA-Systems/4da-mcp-server
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
mcp-scan
Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.
Conning
Run commands on your remote test machines over SSH without the agent ever seeing a secret.
io.github.Toraastrta/sphior-code-mcp
Deterministic SAST/SCA findings + fix guidance for your AI agent. Runs locally, no account needed.
Ziggs
Ziggs delegate MCP: chat, agreements, context, payments via OAuth or operator key.
QuickBooks Online MCP Server
QuickBooks Online MCP server for invoices, customers, and payments. OAuth 2.1 + PKCE, stdio/HTTP.
io.github.carelessdept/ci-guard-mcp
Local-first static repository security and configuration drift auditor (CLI, GitHub Action & MCP).
UML Forge
Architecture intelligence, security analysis, and living docs. 13 Mermaid tools.
MCP Server for OSCAL
AI agent tools for Open Security Controls Assessment Language (OSCAL).
contextweaver
MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.
Forge MCP
MCP server + tools for the Forge E-- generative-music authoring loop (compile / run / commit).
LeanGate
Checks agent-written Python against your repo: duplicate helpers, error handling, security.
io.github.makash/feedmyagent
Technology intelligence feed for AI agents: tech stack, compliance, security.
io.github.michalper/mcp-magento-audit
MCP server for auditing Magento projects: update compatibility, module quality, dependency security
hush
Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
Oura Ring
Read-only Oura Ring sleep, readiness, activity, stress and heart rate data (OAuth2)
WokiToki
Walkie-talkies for AI coding agents: peer-to-peer, end-to-end encrypted messaging via MCP.
MemoraEU
Zero-knowledge persistent memory layer for AI agents. Encrypted client-side, hosted in France.
Security MCP
Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses
ConnectWise PSA
ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, RBAC
MCP Shield
Security scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.
io.github.stasxr/palanit-core
Scan MCP servers and agent tool manifests for poisoning, exfiltration, secrets and supply-chain risk
ForgeBridge
A local, permissioned MCP agent for authorized developer workstations.
VMware Harden
VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.
VMware NSX Security
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
SPARDA
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
LexQ
Policy engine tools: author rules, simulate impact, replay decisions, and deploy.
Fettle
Uptime monitoring for developers — monitors, incidents, heartbeats, maintenance, status pages
Server
MCP server for usegrant
keycloak-mcp-server
Keycloak MCP server that calls the Admin API as the signed-in user, via OAuth
mcp-server-shield
Author-side hardening primitives for Python MCP servers.
nvd-cve-mcp-server
MCP stdio server for querying CVE data from the NVD API v2.0
obsidian-mcp-server
MCP server giving Claude Code read/write access to Obsidian vaults
sonarqube-mcp-server
MCP Server for SonarQube - allows AI assistants to query bugs, vulnerabilities, code smells, security hotspots and more
Server
MCP server for Anlyon. Lets an AI agent invoke named production actions and request human approval, without holding a credential.
Server
MCP server for SixthWall AI code security scanner. Integrates with Claude Code for automatic vulnerability detection with Fix Packs.