@guardbee/mcp-security-proxy
OfficialRelated Servers
Alternatives to @guardbee/mcp-security-proxy
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceProxies MCP traffic between a client and a downstream server to enforce runtime policies on tool declarations, call arguments, and results, including allowlisting, sandboxing, secret and egress controls, and injection detection. It also includes a deterministic benchmark for measuring which security controls stop which attacks.MIT
- AlicenseNot gradedqualityCmaintenanceEnables secure MCP traffic by filtering threats with a 3-stage detection pipeline, applying RBAC policies, and redacting sensitive data in real-time via an SSE-inspecting proxy.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceControl-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.17Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnforces deterministic security policies on Model Context Protocol traffic between agents and remote MCP servers, including request validation, signed human approval, response-side credential blocking, prompt-injection flagging, and privacy-minimized auditing.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to safely access upstream MCP servers through centralized policy enforcement, including allow/deny/approval decisions, schema pinning, circuit breakers, and audit logging.MIT
- AlicenseNot gradedqualityCmaintenanceEnables secure, low-latency proxying of MCP tool calls by detecting and blocking malicious requests such as path traversals and command injections, while redacting leaked credentials.6 npmMIT
TDQS
Scored across 129 tools
The namespace prefixes (e.g. secret_scanner__scan_file vs prompt_leak_scanner__scan_text) make most tools distinguishable, and descriptions clarify domain-specific checks. However, many auditors share near-identical scan_text/scan_file/scan_directory/list_patterns patterns, and overlapping areas such as secret vs prompt-leak vs document scanning or individual auditors vs the owasp_scan meta-tools can cause selection confusion.
Tool names consistently follow a lower_snake_case namespace__action convention, with each auditor or domain grouped under a clear prefix. Minor variations like check_compliance or gateway_status still fit the established pattern, and the overall naming scheme is highly predictable.
At 129 tools, the surface is far beyond the typical 3-15 well-scoped range and exceeds even the heavy 25+ threshold by a wide margin. While the server covers many security domains, the sheer number of closely parallel scan_* tools creates substantial selection overhead for an agent.
Coverage is broad and deep across secrets, dependencies, DNS, TLS, OAuth, prompt injection, MCP configuration, compliance, and vulnerability scanning, with file/text/directory variants and pattern-listing support in most areas. Minor lifecycle gaps remain, such as no baseline deletion for rug-pull detection and limited management operations for gateway policy or global scanner configuration.