"Connecting to SEC EDGAR MCP using Bedrock Models" matching MCP servers:

Enables deterministic auditing of agent skills, system prompts, and downloaded file collections against eight malicious-skill supply-chain patterns, returning line-numbered findings and pass/flag verdicts without using an LLM or network calls.

Enables LLMs and AI agents to perform defensive security posture assessments, privilege escalation surface audits, and post-quantum cryptography readiness checks through read-only diagnostic tools.

Enables passive security scanning of HAR files from QA test automation to detect missing security headers, insecure cookies, CORS misconfigurations, and leaked secrets, without making any live requests.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Exposes existing AWS Lambda functions as MCP tools so AI agents can read and manage orders. Cognito-issued tokens and policy checks control which agents may call data-changing operations.

A Model Context Protocol (MCP) server for Kerberos abuse operations using Rubeus on Windows or Impacket on Linux/macOS.

Provides programmatic access to Mimikatz for credential extraction, Kerberos attacks, SAM/LSA dumping, and other Windows security assessment tasks through natural language.

An MCP server that provides AI assistants with access to CrackMapExec/NetExec network penetration testing capabilities via SSH to a Kali Linux host, supporting multiple protocols for enumeration, credential dumping, and command execution.

Enables AI-assisted vulnerability management by connecting Claude Desktop to local Nessus and Tenable Vulnerability Management, allowing natural-language queries for scan management, threat intelligence enrichment, and prioritized remediation planning.

Enables AWS Bedrock AgentCore agents to perform secretless database queries and cloud service actions through an Akeyless Gateway, with credentials kept off the agent and tool responses limited to paths, metadata, and results. Provides MCP tools for listing secrets, querying databases, executing services, and discovering sub-tools.

Provides a zero-install security baseline for AI coding agents, with tools to retrieve curated security rules and check actions against them for self-correction.

Exposes Lacework API v2 alert operations as MCP tools, allowing AI agents to list, search, and manage alerts with flexible time ranges and authentication.

MCP server for searching NIST's National Vulnerability Database, enabling retrieval of recent CVEs, keyword/CPE/CWE searches, and detailed CVE information.

Enables Windows-native malware analysis and reverse engineering inside Flare-VM by exposing 50 tools for static and dynamic analysis, memory injection scanning, debugging, network simulation, and automated triage playbooks without requiring a Kali Linux host, WinRM, or SMB shares.

Enables blockchain security analysis using GoPlus Security API, providing rug pull detection, phishing site detection, NFT security analysis, and token security assessment across 14+ blockchain networks. Supports comprehensive security analysis for addresses, tokens, and smart contracts through natural language queries.

Enables AI agents to perform safe, authorized penetration testing by managing engagements, enforcing scope and risk policies, and orchestrating tools like Nmap, Nuclei, and Subfinder.

A secure MCP proxy server with JWT authentication, SQL guardrails, rate limiting, and Kafka audit logging, enabling enterprise-grade access control for MCP clients like Cursor and Claude Desktop.

Self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

Enables AI assistants to perform password security auditing using John the Ripper on a remote Kali system via SSH, supporting cracking, hash management, and session control.

MCP server for Technical SEO DNS record auditing, SOA expiry health checks, SSL/TLS inspection, and HTTP security header analysis. Enables comprehensive security audits and scoring via 10 tools.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.

Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.

Provides tools to interact with the OpenCTI platform, including checking if a campaign exists.

Enables administrators to securely record approved parking reservations to a durable text file with validation, concurrency safety, and audit logging.

An MCP server that connects language models to a Wazuh SIEM cluster, enabling read-only plain-language queries, schema inspection, field coverage analysis, and decoder testing.

Inspects documents for tampering, ineffective redactions, and text aimed at language models before they enter an agent's context, and compares documents to confirm whether they are unchanged.

A neutral, public danger grade for MCP servers that AI agents rely on, providing A-F grades and transparency signals to vet servers before connecting.

MCP server for connecting to SQL Server in readonly mode. Allows any MCP client to explore the schema and run SELECT queries against a SQL Server database.

Enables MCP clients to query the ransomware.live PRO threat-intelligence API through 25 read-only tools covering ransomware group TTPs, victims, IOCs, YARA rules, ransom notes, leaked negotiation chats, press coverage, SEC 8-K disclosures, and CSIRT contacts.

Enables AI agents to evaluate trust, safety, and bias of models and agentic traces using TrustModel APIs.