"Methods to Improve or Enhance a Prompt" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables agents to scan incoming emails, web pages and messages for instructions aimed at the AI, wrap that untrusted content in a nonce-bounded fence the content cannot forge, and expose a check_action tool so the model's tool calls can be blocked or confirmed after it reads something from outside. It runs locally over stdio with zero dependencies and no network access.

The control plane for AI prompts that scores, enforces policy, locks config, and audits every prompt decision.

Enables security researchers to evaluate AI system defenses against prompt injection attacks through a comprehensive set of test vectors and analysis tools.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

MCP server exposing prompt-shield's prompt-injection firewall for LLM applications. Four tools — scan_input, scan_output, scan_tool_result (with optional sanitization), and list_detectors — backed by 34+ detectors and a federated ed25519-signed threat feed.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

A standalone MCP server that enforces clean prompt structure, strips model‑invented instructions, and detects capability hallucinations before they propagate through your system.

Provides MCP clients a single decision-only tool to classify prompts as safe for local or cloud models, or as containing PII or jailbreak content, without executing actions or calling AI models.

Enables LLM application builders and security teams to detect and strip prompt injections, scan for secrets, obfuscate PII, and audit synthetic datasets for bias using deterministic tools.

WAF for AI agents — block prompt injection before it reaches the LLM.

Enables MCP-compatible clients to deterministically neutralize adversarial prompt injections and jailbreak overrides with zero-dependency, sub-millisecond heuristic analysis.

Enables deterministic detection and neutralization of adversarial prompt injections and override attempts in AI agent workflows via a zero-dependency MCP server, providing structured telemetry and low-latency validation.

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.

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

Protects AI agents from prompt injection attacks, jailbreak attempts, and common web vulnerabilities by screening untrusted input through semantic LLM analysis and static pattern matching.

Enables MCP clients and autonomous agents to screen incoming prompts for system overrides, delimiter breakouts, and encoded payload evasion, helping block prompt injection and jailbreak attempts before execution.

Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.

Enables AI agents to manage VPN infrastructure through provisioning, lifecycle control, traffic routing, and health monitoring.

Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.