prompt-injection-detector

by found402 · security · mcp-server, smithery

Prompt Injection Detector is a stateless security microservice built for the agent economy. Before your agent acts on any input — whether from a user, an email, a document, or another agent — run it through this scanner first. Detects: jailbreak attempts, instruction overrides, role-play manipulation, goal hijacking (OWASP ASI01), tool misuse patterns (OWASP ASI02), hidden instructions embedded in data, and indirect injection via external content. Returns a confidence score, severity rating, spe

Source: https://smithery.ai/servers/found402/prompt-injection-detector

Install

git clone https://smithery.ai/servers/found402/prompt-injection-detector

Tags: mcp-server, smithery

Source: smithery

About security MCP servers and Claude skills

Security MCP servers let agents scan dependencies, audit logs, check for vulnerabilities, and enforce policy guardrails. Critical for any agent that touches production.

prompt-injection-detector is one of hundreds of security entries indexed on Skiln. Browse the full security category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.

Related security MCPs and skills

  • EveAegis MCP by kakon77777-commits

    An AI-native governance control plane for GitHub portfolios that enables inventory sync, provenance analysis, classification, and policy enforcement across multiple repositories with strong security boundaries.

  • com.skulayer/skulayer by com.skulayer

    The agent-ready product data layer for ecommerce: audit, fix and serve product feeds.

  • acronis-mcp by MSPbotsAI

    MCP server that exposes Acronis Cyber Protect Cloud APIs as 14 read-only tools for managing alerts, tasks, agents, resources, policies, and tenants.

  • claude-token-saver-mcp by BlackFoil

    Enables Claude Code to offload routine code generation and text processing tasks to a local Ollama LLM, saving Cloud API tokens and costs with automatic model selection and security features.

  • mcp-crm by amin-ale

    Enables AI agents to safely operate HubSpot CRM contacts, deals, and pipelines via MCP, with caching, idempotency, audit trails, and robust error handling.

  • cPanel MCP Server by hahsanayub

    Enables AI assistants to manage cPanel hosting accounts including DNS, email, databases, SSL, files, security, and more through natural language using cPanel's UAPI and API2.

  • EVIDIQ Sentinel MCP by evidiq

    Scans remote MCP endpoints, manifests, and agent skills for security threats, providing deterministic scores, verdicts, and signed reports to verify agent infrastructure before trust or payments.

  • DefectDojo MCP Server by dcianciulli

    A Model Context Protocol (MCP) server that provides comprehensive access to DefectDojo vulnerability management platform.

Frequently asked questions

How do I install prompt-injection-detector?

Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.

Which clients support prompt-injection-detector?

Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.

Is prompt-injection-detector free?

The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.