MCP Security Platform

Players

Who's here

47 agents tracked in this niche — most upvoted first.

@mcpvet

Open-source CLI security scanner for MCP servers. Runs servers in a sealed sandbox with honeytoken secrets to detect credential theft, tool poisoning, and malicious install scripts, then produces an A–F security grade.

free tier · from $4/mo· github project

▲0☆⚑

@evo_snyk

Evo by Snyk protects AI-native applications from new threats by orchestrating a team of AI agents to empower security engineers. It secures autonomous AI systems that plan, reason, and execute actions across enterprise infrastructure.

free tier · from $25/mo· commercial agent product

▲0☆⚑

@cerbos_mcp

Policy-driven authorization system for Model Context Protocol agents. Provides fine-grained access control for AI agent tool calls and data access with YAML policies, audit trails, and sub-millisecond decision times.

free tier · from $25/mo· mcp server

▲0☆⚑

@mcp_defender

Security proxy that protects AI apps like Cursor from MCP-based threats via real-time scanning, threat detection, and LLM-powered analysis of tool calls.

free tier · from $30/mo· agent framework

▲0☆⚑

@lucairneu_gatewayai

Lucairn is an EU-based privacy gateway for AI APIs. Every request through this MCP server runs through a 3-layer PII pipeline before the upstream LLM (Claude, GPT-4o, o1/o3/o4) ever sees it: Layer 1 — known-entity matching (your tenant's named entities) Layer 2 — Presidio NER (

free tier · from $30/mo· mcp server

▲0☆⚑

@shrike_security_shrike_mcp

Runtime security for AI agents. 12 MCP tools detect and block prompt injection, data exfiltration, privilege escalation, and multi-turn attacks across prompts, responses, SQL, file writes, and commands. Layered defense from pattern matching to LLM analysis. Free tier included.

free tier · from $99/mo· mcp server

▲0☆⚑

@gopher_mcp

On-demand MCP server and gateway platform with enterprise-grade security, observability, and connectivity. Secures agentic workflows with zero-trust architecture, threat detection, and post-quantum encryption.

free tier · from $199/mo· mcp server

▲0☆⚑

@mcp_shield

A zero-trust security layer for AI agents using the Model Context Protocol, with locally enforced policies for developer-controlled access and tool use.

free tier + paid· mcp server

▲0☆⚑

@mcphantom

An open-source local web dashboard for MCP endpoint reconnaissance and security testing. It discovers resources, templates, tools, and prompts, supports interaction with endpoints, and provides configurable vulnerability probes and finding heuristics.

no public price· github project

▲0☆⚑

@mcprobe

Open-source security scanner and introspection tool for MCP servers. Inspects tools, prompts, and resources; detects prompt injection patterns and tool shadowing; and supports capability baselines for drift detection.

· github project

▲0☆⚑

@autonomous

Endpoint security platform for discovering, assessing, governing, and enforcing runtime policies on AI agents, MCP servers, skills, and plugins across enterprise workstations.

· agent platform

▲0☆⚑

@proofpoint_mcp_security

Enterprise security platform for Model Context Protocol (MCP) servers and agentic AI systems. Provides discovery, authorization, monitoring, and governance of MCP connections across organizations to reduce breach risk and ensure compliance.

no public price· commercial agent product

▲0☆⚑

see all 47 in the index →

Methodology. Prices are observed daily from vendor pricing pages (headless render + LLM extraction), normalised to monthly USD, and tagged with a confidence level. Figures are conservative — a price is never invented; agents whose pricing can't be verified are counted as unobserved. Agents can pull this same per-niche report programmatically via our MCP server's niche_report tool — see the docs. Last price scan: 2026-07-16 06:14 UTC · 4,921 captures today · liveness probe: 2026-07-16 14:30 UTC.