Security MCP servers for scanning, threat intelligence and audits: let an AI assistant check code, dependencies and infrastructure for risks. 3,540 servers in this category.
Assess the reliability and security of MCP servers through runtime behavioral trust scoring and pre-invocation verification.
$claude mcp add --transport http dominion-observatory-80868e https://dominion-observatory.sgdata.workers.dev/mcpProvides runtime behavioral trust scoring and reliability metrics for MCP servers to help AI agents assess security before invocation.
$claude mcp add --transport http dominion-observatory https://dominionobservatory.com/mcp
Performs privacy and public-exposure analysis for authorized users and agents, including metadata audits, breach checks, and wallet hygiene reviews.
$claude mcp add --transport http phantomoperator https://freysaai.freysa.dev/mcp
Performs HTTPS audits, CSR generation, certificate decoding, and format conversions for SSL/PKI management.
$claude mcp add --transport http ssl-toolkit-mcp https://tools.idigitrust.com/api/v1/mcp
Provides a pre-execution decision layer that evaluates autonomous agent actions against policies to return allow, review, or block decisions.
$claude mcp add --transport http ai-risk-oracle https://api.interailabs.dev/mcp
Translates complex crypto wallet approvals and signature requests into plain language verdicts like SAFE, CAUTION, or RISK.
$claude mcp add --transport http smartcontractexplainer https://plaintext.fizzl.eu/mcp
Enforces deterministic step order and provides verifiable audit receipts for AI agent tool calls to prevent procedural hallucinations.
$claude mcp add --transport http agenticrail-mcp https://mcp.agenticrail.nz/
Enables an AI agent to send and read end-to-end encrypted documents while keeping private keys and plaintext on the local machine.
$claude mcp add armadoc -- npx -y armadoc
Scans AI agent skills and configuration files for prompt injection, hidden Unicode instructions, exfiltration commands, and over-broad permissions.
$claude mcp add --transport http agent-skill-audit-mcp https://agent-skill-audit-mcp.mcpize.run/mcp
Lets an AI client check website trust scores, community ratings, and domain reputation data.
$claude mcp add mcp-server-truster -- npx -y mcp-server-truster
Analyzes domain email security by grading SPF, DMARC, DKIM, and MX records via public DNS to identify spoofing vulnerabilities.
$claude mcp add --transport http deliverability-doctor https://deliverability-doctor.deliverability-doctor.workers.dev/mcp
Allows AI clients to request Nostr signatures through browser extensions or remote signers without exposing private keys.
$claude mcp add --transport http nostr-signer-chatgpt https://signer.frontiercrown.com/mcp
Analyzes MCP server source code to report potential risks and behaviors before you connect them to your AI agent.
$claude mcp add --transport http sri https://sri-test.biz/mcp
Provides multi-model review tools and local pre-commit gates to audit risky AI-generated code changes before they are committed or shipped.
$claude mcp add --transport http init https://mcp.truverif.ai/mcp
Evaluates the security and trust scores of MCP servers, AI skills, and npm packages using safety scanning and multi-dimensional signals.
$claude mcp add mcpskills-server -- npx -y @mcpskillsio/server
Provides a local gateway for managing approved MCP jobs, tracking agent permissions, and inspecting durable retry history.
$claude mcp add continuity-gateway -- npx -y @ramex-labs/continuity-mcp-gatewayProvides a process supervisor for recording agent roles, permissions, and unfinished duties to ensure durable responsibility during agent transitions.
$claude mcp add continuity -- npx -y @ramex-labs/continuity-mcp
Scans text for leaked credentials like API keys and private keys locally before an agent writes or commits data.
$https://github.com/agentic-income-bot/mcp-secret-scan/releases/download/v1.0.0/mcp-secret-scan-1.0.0.mcpb
Provides local, privacy-first utility tools for redacting sensitive data, decoding JWTs, estimating LLM costs, and hashing text without network calls.
$claude mcp add omnideck-mcp -- npx -y omnideck-mcp
Performs read-only preflight reviews of npm packages and project dependencies to detect high-risk behaviors before execution.
$claude mcp add npm-vibe-check -- npx -y npx-vibe