"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

Enables AI assistants to register prompts for security verification, checking for hidden injections, data exfiltration patterns, and jailbreak attempts, then generate embed codes for displaying security badges on websites.

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

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.

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

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.

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

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 generating secure passwords, exposing password policies, and providing reusable prompt templates for secure password creation through MCP primitives.

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.

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.

Enables agents and applications to detect, inspect, and neutralize prompt injection, jailbreak attempts, and hidden instruction escapes in untrusted text before it is passed into prompts.

Enables agents to scan untrusted text for jailbreak markers, prompt-override exploits, and indirect injection payloads, then cleanse it by replacing hostile command sequences with safe placeholders before the text reaches a prompt. Exposes tools for sanitizing input and itemizing detected threat patterns.

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.

It lets users manage a pfSense firewall conversationally from Claude Desktop, Claude Code, or any MCP client — creating and reordering firewall rules, NAT, VPN tunnels, DNS, DHCP, certificates, and running diagnostics. Every configuration change passes through safety guardrails with confirmation prompts, rate limits, and rollback points.

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

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.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

Enables AI agents to scan text for leaked secrets and prompt injection markers, and redact them before reaching an LLM.

Provides prompt injection detection, PII/secrets redaction, and an audit trail for AI agents via MCP tools.

Protects AI agents from threats like prompt injection, jailbreaks, and SQL injection through a multi-layer scanning pipeline. It also enables PII redaction and rehydration to ensure data privacy during LLM interactions.

Security scanner for AI agent packages that enables AI agents to audit MCP servers and packages for vulnerabilities, prompt injection, and supply chain attacks.

Open-source permission control plane for AI agents — scan, enforce, and audit every tool call with code-level policies that prompt injection can't bypass.

▎ Check an email before an AI agent sends it: send / ask a human / block — with machine reason codes and prompt-injection detection.

Vet ClawHub skills before installing them; detects prompt-injection, exfiltration, and other security issues, outputting a risk score with per-finding evidence.

A remediation orchestrator exposed as an MCP server that provides primitives for SSH host inventory, CVE matching, live advisory lookups, compliance mapping, and Ansible playbook generation.

Runtime governance proxy for MCP tool calls. Inspects tool results for prompt injection and capability abuse before they reach your agent, blocking attacks that exploit the MCP trust boundary.

MCP server that scores text, web pages and MCP tool definitions for prompt injection and tool poisoning.