"The most widely used models" matching MCP servers:

Securedact MCP is a local-first privacy layer for MCP-compatible AI workflows. It detects, reviews, redacts, and audits sensitive information before approved sanitized content is used downstream.

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.

Enables Claude to look up known vulnerabilities in a project's dependencies across OSV.dev, CVE.org, NVD, CISA KEV and EPSS, then rank the findings by real-world exploitation so the most urgent fixes surface first. It supports single-package checks, keyword CVE searches, and whole-lockfile scans, with upgrade-path reasoning.

Enables agents and security automation to adjudicate proposed defense mutations against a sealed, canonicalized attack scenario, enforcing reproduction, impact-screening, regression, and proven-improvement gates before promoting at most one candidate. Every verdict, rejected candidate, and rejection reason is sealed into a recomputable SHA-256 Merkle evidence root and hash-linked lineage that can be independently verified without trusting the server.

A security-hardened Postgres MCP server that enables LLM agents to run safe, read-only SQL queries with enforcement via SQL-AST inspection and read-only transactions.

Exposes user, membership, and role administration tools via MCP, acting as a thin passthrough to a coordinator API with RBAC enforced by the coordinator using caller bearer tokens.

An AI-driven Android dynamic analysis tool that enables AI models to perform automated reverse engineering by controlling Frida. It provides capabilities to inject scripts, manage application processes, and analyze real-time execution data through the Model Context Protocol.

MCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).

Azure PIM role activation MCP server allowing role activation through natural language, with support for saving frequently-used roles as favorites and activating them with a single command.

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.

Enables users to manage OpenFGA authorization models, stores, and relationship tuples through natural language. It supports permission checks, batch tuple operations, and the deployment of authorization models across different environments.

Living off the Land intelligence for AI agents. GTFOBins, LOLBAS, LOOBins, LOLDrivers, LOLRMM, WADComs, LOLC2 and more — unified into a single MCP server.

Enables AI assistants to perform quantum-resistant cryptographic operations using NIST-standardized algorithms including ML-KEM, ML-DSA, and SPHINCS+. Supports key generation, encryption, digital signatures, and security analysis for post-quantum cryptography research and development.

Enables AI agents to perform general-purpose open-source intelligence lookups across domains, infrastructure, identity, social media, and threat/breach sources through a unified MCP interface, with most tools free and no API keys required.

A Model Context Protocol server that retrieves CVE information from the National Vulnerability Database, allowing AI models to access up-to-date vulnerability data.

Enables detection of AI-generated content from ChatGPT, GPT-4, and Gemini models through the BACH AI Content Detector API.

Lets AI coding agents generate and manage threat models, controls, assumptions, compliance mapping, and evidence programmatically via the Mipiti security posture platform.

An implementation of the Model Context Protocol server that enables AI models to communicate with Edge Security Acceleration (ESA) services, allowing models to manage routines, deployments, routes, records, and sites through standardized protocols.

MCP server for the Tenable Identity Exposure API, providing 131 tools for complete API coverage with multi-tenant support and granular security controls.

the-real-unifi-mcp License: MIT Node MCP SDK [![CI](https://github.com/mguttmann/the-real-unifi-mcp/actions

A read-only MCP server over a published model catalogue that lets agents search and resolve models, fetch overlay profiles, definitions and citations, and check memory records against a governance overlay through the same code path as the CLI.

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

Proxy that wraps any MCP server and masks PII in outbound tool-call arguments before they reach the backend tool, restoring the originals in the results. Covers generic PII plus Indian identifiers (Aadhaar, PAN, GSTIN, UPI, IFSC, ABHA) that most detectors miss.

Enables Claude, Cursor, or any MCP-compatible client to query Apache Kafka topics, consumer groups, schemas, and cluster health in natural language, served from your own self-hosted instance. Access is read-only and inherits the token holder's existing RBAC, so only metadata reaches the model unless a capped message-reading tool is explicitly used.

A Model Context Protocol server that enables AI agents to interact with Netwrix Access Analyzer through standardized interfaces, allowing visibility into data access risks, data classification, and user access patterns to help organizations better secure their most sensitive data.

Rate-limits MCP tool calls with Upstash Redis, allowing a configurable number of invocations per sliding window and sharing counters across server instances.

Serves three MCP tools over stdio that answer typed questions — yes/no, choice, and score — as calibrated probabilities instead of prose, with an offline mock provider used by default. Egress is opt-in and disclosed per feature, and a missing live credential fails fast at startup rather than surfacing per call.

Enables agents to run static heuristic scans over a repository path via stdio, surfacing review candidates with file:line evidence for web3 auth and payment vulnerability patterns. Results can be used as CI-style gates or triage input without any dataflow analysis or external dependencies.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Local stdio MCP server for Bitwarden (Public API + Secrets Manager). 50+ admin tools for members, groups, collections, policies, licensing, projects, and secrets. For Claude Desktop / Claude Code.