Skip to main content
Glama

Related Servers

Alternatives to agent-firewall

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      A security gateway that sits between an MCP client and real MCP servers, routing every tool call through namespace isolation, definition pinning, argument and rate policies, taint tracking, and response injection checks. It blocks tool shadowing, rug pulls, hidden Unicode payloads, path traversal, and exfiltration of private data to outside channels, while logging each decision and requiring out-of-band human approval for sensitive calls.
      19 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides a three-layer firewall for MCP servers that inspects tool outputs for malicious content, enforces egress destination policies, and gates consequential tool calls. It runs as both a proxy and an MCP server, enabling agents to scan content, check tool calls, and evaluate results before they reach the model.
      34 npm
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables safe use of any MCP server by proxying and live-scanning all tool requests and responses, blocking or redacting poison descriptions, indirect prompt injection, malicious arguments, and unauthorized destinations.
      -
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      A transparent proxy and execution firewall that intercepts and audits AI agent tool calls against configurable security policies before forwarding them to downstream MCP servers. It provides safe execution environments with features like data redaction, anti-loop protection, and unified alert dispatching.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables IT service-desk agents to route every tool call through Clocked's Guard, Protect and Inspect endpoints, screening untrusted inbox and ticket content for prompt injection, anonymizing PII before it reaches the model, and vetting proposed remediation scripts for approval or denial. It sits between an MCP client and the agent's tools, so results and actions are gated by allow, hold, cut, or deny verdicts.
      9 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables secure runtime mediation of tool requests from MCP-connected AI agents, enforcing least-privilege policies, validating intent and inputs, detecting multi-step attacks and information leaks, and supporting explainable decisions, audit trails, and human approval for sensitive actions.
      MIT

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues