"Understanding Boss Mode" matching MCP servers:

Guardrail proxy for AI agents on SQL Server. Each statement runs as the caller's own login, a T-SQL parser blocks dangerous statements, and every statement is audited. Local stdio mode or a central Docker service.

Enables an AI assistant to read Interactive Brokers account and market data and to prepare order drafts that the user approves inside IBKR, while blocking any order submission to live markets. An opt-in paper-trading mode additionally allows simulated orders to paper accounts only, with per-order confirmation and logging.

MCP server that exposes Bitwarden's Public API for organization member and vault group management, enabling inviting members and assigning them to vault groups. Supports stateless, multi-tenant authentication via gateway mode or env-based credentials.

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.

Mechanical write gates, evidence receipts, and adversarial review for AI coding agents. Fable Mode enforces a Think → Prove → Attack → Write workflow before an agent earns permission to edit a workspace.

Enables AI agents to securely read and write SAP ABAP development objects via the ADT REST API, enforcing policy-based guardrails such as package/namespace allow-lists, read-only mode, human approvals, and audit logging.

Provides MCP tools to query the Tenable Identity Exposure (TIE) API for security profiles, deviances, attacks, and activity timelines, with enforced read-only mode to protect credentials.

Strict AI code reviewer powered by Groq. Finds bugs, vulnerabilities and security issues in your code. Supports analyze, compare versions, explain code, generate tests, and HTML reports.

Enables AI clients to perform controlled diagnostics and configuration of Keenetic and Netcraze routers over LAN RCI or remote KeenDNS HTTPS, with read-only mode, guarded writes, and centralized secret masking.

Secrets vault for Claude Code. Encrypt API keys, tokens and passwords with AES-256. Full audit logs, MCP access rules, and zero-knowledge mode. Secrets never appear in chat.

An MCP server for ManageEngine Endpoint Central that enables querying managed computers, inventory, patches, vulnerabilities, and more via its REST API, with read-only mode by default and optional write capabilities.

Enables Discord server moderation actions including kick, ban, timeout, role management, channel operations, audit logs, and member management through MCP tools.

Enables querying Wazuh 5 agents, groups, cluster status, MITRE techniques, events, findings, and vulnerability state through the manager and indexer APIs, with optional agent restart when read-only mode is disabled.

Security gateway that wraps any MCP server with per-tool policies, approval gates, and optional Ed25519-signed decision receipts. Shadow mode logs every tool call without blocking; enforce mode applies block, rate-limit, and minimum-tier rules. Receipts are independently verifiable offline with no accounts needed.

Enables automated pull request review, security vulnerability analysis, and code quality improvement suggestions through any MCP client.

An MCP server that connects AI assistants to the ThreatLocker Portal API with 44 tools for managing computers, approvals, action logs, tags, maintenance mode, and more across single-org and multi-tenant setups.

Enables AI assistants like Cursor, Claude, and Codex to interact with Krutrim Cloud, providing discovery and controlled operations for VPCs, compute, storage, networking, Kubernetes, KPods, and IAM, with safety controls such as confirmation and read-only mode.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

A security layer for AI agents that monitors, checks, and records every action, providing a trust light, timeline, rewind, and ghost mode for testing without consequences.

Enables local, privacy-mode incident handoffs with four fixed questions, pattern-guarded redaction, human-review drafts, and optional in-memory data clearing.

Enables a language model to inspect proxy history, run scoped scans and intruder jobs, and drive a proxied browser through Burp Suite for authorized security testing on test and staging environments. Scope, environment, mode, rate limits, refusals and secret redaction are enforced in gateway code with a tamper-evident audit log.

Enables AI agents to inspect and manage Windows software, including listing installed and running apps, searching catalogs, installing, upgrading, uninstalling, managing startup apps, exporting backups, and checking exploited vulnerabilities. It also supports a read-only mode for safe discovery.

Enables AI agents to interact with Fortinet FortiManager through a minimal MCP interface using sandboxed JavaScript for querying the API spec and executing JSON-RPC calls.

Connects your Bradescard account to AI assistants via Open Finance Brasil, enabling natural language queries about balances, statements, credit card bills, and investments in read-only mode.

Enables debugging of bunny.net CDN pull zones — inspecting edge rules, cache purges, statistics and origin error logs — and managing bunny Shield WAF settings, custom rules, rate limits, bot detection and WAF event logs, with credential redaction and before/after change diffs. A read-only mode can restrict it to inspection tools.

Audits MCP server configurations for security risks including capability inventory, SSRF, prompt injection, and drift detection. Works in read-only mode and can also be used as an MCP server to let AI agents audit their own attack surface.

Enables MCP clients such as Cursor to connect to the WoWSQL API over authenticated HTTP using OAuth 2.0 with PKCE, with project scoping, read-only mode, and selectable features.

Adds team-gateway mode and Microsoft SSO to Odoo MCP, allowing business users to authenticate via OAuth 2.1 and execute tool calls with their own Odoo permissions, ACLs, and audit trails.

MCP server providing a searchable security knowledge base for AI coding assistants, enabling retrieval of secure-coding instructions and feature-specific security guidance.

Enables AI clients to safely inspect and query PostgreSQL databases in read-only mode through MCP, with single-statement SQL execution, table listing, table description, and schema resources.

Enables AI agents to safely query Kingdee Cloud Galaxy ERP with read-only mode, write confirmation gates, and full audit logging.

The only Multi-LLM Compliance Engine (GPT-4o + Claude + DeepSeek). Auto-fix GDPR/LGPD risks and more 15 frameworks. code.guard.eu

A secure MCP server for local API credential management using JSON storage and a read-only default mode. It allows users to list, retrieve, and manage credentials via simple command-line tools and environment-based configuration.

Lets AI agents message other agents and the agents of family and friends, in direct or group chats with files. End-to-end encrypted between bots in private mode, with a self-hostable messaging core.

Enables Claude to manage a self-hosted PocketBase instance: querying and editing records, inspecting and changing collection schemas, handling files, users and backups, and auditing API rules for exposure risks. Writes are gated by a read-only mode plus a two-step confirmation that returns a preview diff and single-use token, so nothing changes until the identical call is approved.

Sits between an AI client and Robinhood Agentic Trading so that reads pass straight through while every order is checked by plain code against user-set caps, cooldowns, market hours, earnings, and blocklists, holding anything that trips a rule or cannot be read. Runs in paper, dry-run, or armed live mode and records each decision in a hash-chained audit log.

MCP server that provides AI coding assistants with access to call graphs, data flows, and security analysis for multi-file vulnerability detection.

Enables AI assistants to manage Okta users, groups, applications, policies, group rules, and system logs through the Okta API. Includes dry-run safety guardrails, confirmation flags, and a read-only inspection mode.

Model-agnostic cybersecurity MCP server for CMMC 2.0 compliance workflows with air-gapped Ollama mode.

A collection of MCP servers for Kali Linux that empower AI Agents in reverse engineering and security testing, providing network analysis, target sniffing, traffic analysis, binary understanding, and automation capabilities.