"Persistent" matching MCP servers:

A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.

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.

Provides persistent memory, cryptographic audit trail, and HMAC-verified skill admission for Claude Code, running locally on PostgreSQL with zero cloud sync.

Provides persistent SSH/PTY sessions to a bastion host with asset discovery, permission-gated audited command execution, and batch operations across multiple targets.

Provides a persistent headed CloakBrowser session with encrypted vault import, account listing/filling, password saving, and fingerprint health checks for LLM agents.

A local capability layer for AI agents providing persistent memory, credential management, connectors, and activity tracking.

Transforms codebases into a living knowledge graph with AI-powered code analysis, security scanning, and persistent semantic memory, leveraging Oracle 26ai vector and property graph capabilities.

MCP server for the Forcepoint DLP 9.0 REST API. Enables incident management, policy management, and authentication via natural language, with multi-user support and persistent storage in Postgres and Vault.

Sovereign autonomous mailbox and identity layer for AI agents, providing persistent email identities, object-level security, OTP/2FA capture, link safety analysis, and event-driven email handling via MCP.

MemoraEU gives your AI a persistent, encrypted memory — sovereign, zero-knowledge, hosted in Europe. Works with Claude, Cursor, Windsurf, ChatGPT via MCP. Self-host for free (AGPL v3) or use the managed EU cloud.

An MCP server that provides ephemeral credentials and persistent MCP connections for AI coding agents, enabling secure access to services like GitHub and AWS without exposing secrets to the agent.

Enables provider-neutral policy enforcement, identity, persistent storage, and telemetry collection for reinforcement learning, evaluation, analytics, replay, and downstream dataset generation across standalone applications and agent systems.

This MCP server offers 72 typed tools for Kali Linux pentesting, including recon, web, AD, cracking, C2, remote desktop, and tunneling. It provides structured JSON output, persistent session state, and auto-populated findings for streamlined workflows.

A Kali Linux-based MCP server that exposes over 45 penetration testing tools for AI-assisted security auditing and vulnerability scanning. It features strict scope enforcement, structured output parsing, and persistent finding storage to automate the offensive security workflow.

A persistent MCP server that securely manages Plaid bank connections, allowing AI assistants to query financial data (balances, transactions, investments, etc.) without exposing sensitive credentials.

Enables local, persistent analysis of business workflows and application state from imported Burp XML or HAR traffic, building actor/entity/state graphs and generating testable hypotheses for manual validation during authorized security testing.

Provides cryptographic identity and signing capabilities for AI agents, enabling them to create persistent identities, sign actions with private keys, and allow external systems to verify the authenticity and provenance of agent-initiated operations.

Enables secure execution of shell commands through a dynamic approval system that prompts for user authorization on first use, with persistent command storage and comprehensive audit logging.

An MCP server that gives AI clients controlled access to a real headless browser with domain allowlisting, SSRF protection, per-session isolation, audit logging, and persistent cookies/state across restarts.

Provides AI agents with persistent identities (Weid numbers) and a friend-based messaging system, enabling cross-platform AI-to-AI communication through 11 MCP tools.