Skip to main content
Glama
@guardbee/mcp-security-proxy

@guardbee/mcp-security-proxy

Official

Related Servers

Alternatives to @guardbee/mcp-security-proxy

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Proxies 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
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables 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
    • A
      license
      Not graded
      quality
      C
      maintenance
      Control-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.
      17
      Apache 2.0
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enforces 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.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables 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
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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.
      15 npm
      MIT

    TDQS

    B3.1/5.0

    Scored across 130 tools

    Disambiguation3/5

    The module prefixes and detailed descriptions help distinguish scanners, but the set contains many overlapping scan_text/scan_file/scan_directory/list_patterns families plus multiple meta-orchestrators (owasp_scan_path, vulnerability_scanner, threat_rules). An agent must read descriptions carefully to choose between secret/prompt-leak/document scanners, OWASP meta-scans and individual auditors.

    Naming Consistency4/5

    Names are consistently snake_case and mostly use a predictable module__verb_noun pattern. Minor deviations exist, such as gateway_status, scan_and_report, and baseline_server/check_server, but overall the convention is clear.

    Tool Count1/5

    130 tools is far beyond a well-scoped set and creates a severe selection burden for an agent. Although many tools map to distinct security domains, the repeated action variants across dozens of modules make the surface extremely heavy.

    Completeness4/5

    Coverage is very broad, spanning OWASP MCP categories, secrets, dependencies, TLS/DNS, models, vector stores, compliance, red-teaming, and runtime gateway auditing. Some lifecycle gaps remain, such as baseline deletion/update and gateway policy mutation, but the core scanning and reporting surface is extensive.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues